{"items":[{"id":598,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"AI threats in the wild: The current state of prompt injections on the web","summary":"Posted by Thomas Brunner, Yu-Han Liu, Moni Pande\nAt Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now,\nIndirect Prompt Injection (IPI)\nis a top priority for the security community, anticipating it as a primary attack vector for adversaries to target and compromise AI agents. But while the danger of IPI is widely discussed, are threat actors actually exploiting this vector today – and if so, how?\nTo answer these questions and to uncover real-world abuse, we initiated a broad sweep of the public web to monitor for known indirect prompt injection patterns. This is what we found.\nThe threat of indirect prompt injection\nUnlike a direct injection where a user \"jailbreaks\" a chatbot, IPI occurs when an AI system processes content—like a website, email, or document—that contains malicious instructions. When the AI reads this poisoned content, it may silently follow the attacker's commands instead of the user's original intent.\nThis is not a new area of concern for us and Google has been working tirelessly to combat these threats. Our efforts involve cross-functional collaboration between researchers at Google DeepMind (GDM) and defenders like the Google Threat Intelligence Group (GTIG). We have previously detailed\nour work in this area\nand\nresearchers have further highlighted\nthe evolving nature of these vulnerabilities.\nDespite this collective focus, a fundamental question remains: to what degree are real-world malicious actors currently operationalizing these attacks?\nProactive monitoring at Google\nThe landscape of IPI on the web\nThere are many channels through which attackers might try to send prompt injections. However, one location is particularly easy to observe - the public web. Here, threat actors may simply seed prompt injections on websites in hope of corrupting AI systems that browse them.\nPublic\nresearch\nconfirms these attacks are possible; consequently, we should expect real-world adversaries to exploit these vulnerabilities to cause harm.\nThus, we ask a basic question: What outcomes are real attackers trying to achieve today?\nFor ease of access and reproducibility, we chose to use\nCommon Crawl\n, which is a large repository of crawled websites from the English-speaking web. Common Crawl provides monthly snapshots of 2-3 billion pages each. These are mostly static websites, which includes self-published content such as blogs, forums and comments on these sites, but as a caveat it does not contain most social media content (e.g., LinkedIn, Facebook, X, …) as Common Crawl skips websites with login walls and anti-crawl directives.\nThis means that, while prompt injections have been observed on social media, we reserve these for an upcoming separate study. For a first look, we can observe prompt injections even in standard HTML, for which Common Crawl conveniently provides not just the source, but also the parsed plaintext.\nThe challenge of false positives\nThe task of scanning large amounts of documents for prompt injections may sound simple, but in reality is hindered by an overwhelming number of false positive detections.\nEarly experiments revealed a significant volume of \"benign\" prompt injection text, which illustrates the complexity of distinguishing between functional threats and harmless content. Many prompt injections were found in research papers, educational blog posts, or security articles discussing this very topic.\nFalse positives: Most prompt injections in web content tend to be education material for researchers.\n(Source: GitHub/swisskyrepo)\nWhen searching for prompt injections naively, the majority of detections are benign content – false positives in our case. Therefore, we opted for a coarse-to-fine filtering approach:\nPattern Matching\n: We initially identified candidate pages by searching for a range of popular prompt injection signatures, like\n“ignore … instructions”\n,\n“if y…","url":"http://security.googleblog.com/2026/04/ai-threats-in-wild-current-state-of.html","published_at":"2026-04-23T21:38:00Z","updated_at":"2026-04-23T21:38:06Z","fetched_at":"2026-11-21T19:15:07.449272Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":true,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/598","html":"https://vulnwatch.ve1ve2.com/item/598"}},{"id":599,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Bringing Rust to the Pixel Baseband","summary":"Posted by Jiacheng Lu, Software Engineer, Google Pixel Team\n\nGoogle is continuously advancing the security of Pixel devices. We have been focusing on hardening the cellular baseband modem against exploitation.\nRecognizing the risks\nassociated within the complex modem firmware, Pixel 9 shipped with\nmitigations\nagainst a range of memory-safety vulnerabilities. For Pixel 10, Google is advancing its proactive security measures further. Following our previous discussion on\n\"Deploying Rust in Existing Firmware Codebases\"\n, this post shares a concrete application: integrating a memory-safe Rust DNS(Domain Name System) parser into the modem firmware. The new Rust-based DNS parser significantly reduces our security risk by mitigating an entire class of vulnerabilities in a risky area, while also laying the foundation for broader adoption of memory-safe code in other areas.\n\nHere we share our experience of working on it, and hope it can inspire the use of more memory safe languages in low-level environments.\n\nWhy Modem Memory Safety Can’t Wait\n\nIn recent years, we have seen increasing interest in the cellular modem from attackers and security researchers. For example, Google's Project Zero\ngained remote code execution\non Pixel modems over the Internet. Pixel modem has tens of Megabytes of executable code. Given the complexity and remote attack surface of the modem, other critical memory safety vulnerabilities may remain in the predominantly memory-unsafe firmware code.\n\nWhy DNS?\n\nThe DNS protocol is most commonly known in the context of browsers finding websites. With the evolution of cellular technology, modern cellular communications have migrated to digital data networks; consequently, even basic operations such as call forwarding rely on DNS services.\n\nDNS is a complex protocol and requires parsing of untrusted data, which can lead to vulnerabilities, particularly when implemented in a memory-unsafe language (example:\nCVE-2024-27227\n). Implementing the DNS parser in Rust offers value by decreasing the attack surfaces associated with memory unsafety.\n\nPicking a DNS library\n\nDNS already has a level of support in the open-source Rust community. We evaluated multiple open source crates that implement DNS. Based on\ncriteria shared in earlier posts\n, we identified\nhickory-proto\nas the best candidate. It has excellent maintenance, over 75% test coverage, and widespread adoption in the Rust community. Its pervasiveness shows its potential as the de-facto DNS choice and long term support. Although hickory-proto initially lacked\nno_std\nsupport, which is needed for Bare-metal environments (see our\nprevious post\non this topic), we were able to add support to it and its dependencies.\n\nAdding\nno_std\nsupport\n\nThe work to enable\nno_std\nfor hickory-proto is mostly mechanical. We shared the process\nin a previous post\n. We undertook modifications to hickory_proto and its dependencies to enable\nno_std\nsupport. The upstream\nno_std\nwork also results in a\nno_std\nURL parser, beneficial to other projects.\n\nhttps://github.com/hickory-dns/hickory-dns/pull/2104\n\nhttps://github.com/servo/rust-url/pull/831\n\nhttps://github.com/krisprice/ipnet/pull/58\n\nThe above PRs are great examples of how to extend\nno_std\nsupport to existing std-only crates.\n\nCode size study\n\nCode size is the one of the factors that we evaluated when picking the DNS library to use.\n\nCode size\nby category\n\nRust implemented Shim that calls Hickory-proto on receiving a DNS response\n\n4KB\n\ncore, alloc, compiler_builtins\n(reusable, one-time cost)\n\n17KB\n\nHickory-proto library and dependencies\n\n350KB\n\nSum\n\n371KB\n\nWe built prototypes and measured size with\nsize-optimized settings\n. Expectedly,\nhickory_proto\nis not designed with embedded use in mind, and is not optimized for size. As the Pixel modem is not tightly memory constrained, we prioritized community support and code quality, leaving code size optimizations as future work.\n\nHowever, the additional code size may be a blocker for other embedded sy…","url":"http://security.googleblog.com/2026/04/bringing-rust-to-pixel-baseband.html","published_at":"2026-04-10T15:12:00Z","updated_at":"2026-04-10T15:12:43Z","fetched_at":"2026-11-21T19:15:07.449276Z","severity":"unknown","cvss_score":null,"epss":0.0032,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":"CVE-2024-27227","vuln_ids":["CVE-2024-27227"],"tags":["android","android security","pixel"],"cluster_id":443,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/599","html":"https://vulnwatch.ve1ve2.com/item/599"}},{"id":600,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Protecting Cookies with Device Bound Session Credentials","summary":"Posted by Ben Ackerman, Chrome team, Daniel Rubery, Chrome team and Guillaume Ehinger, Google Account Security team\n\nFollowing our April 2024\nannouncement\n, Device Bound Session Credentials (DBSC) is now entering public availability for Windows users on Chrome 146, and expanding to macOS in an upcoming Chrome release. This project represents a significant step forward in our ongoing efforts to combat session theft, which remains a prevalent threat in the modern security landscape.\n\nSession theft typically occurs when a user inadvertently downloads malware onto their device. Once active, the malware can silently extract existing session cookies from the browser or wait for the user to log in to new accounts, before exfiltrating these tokens to an attacker-controlled server. Infostealer malware families, such as LummaC2, have become increasingly sophisticated at harvesting these credentials. Because cookies often have extended lifetimes, attackers can use them to gain unauthorized access to a user’s accounts without ever needing their passwords; this access is then often bundled, traded, or sold among threat actors.\n\nCrucially, once sophisticated malware has gained access to a machine, it can read the local files and memory where browsers store authentication cookies. As a result, there is no reliable way to prevent cookie exfiltration using software alone on any operating system. Historically, mitigating session theft relied on detecting the stolen credentials after the fact using a complex set of abuse heuristics – a reactive approach that persistent attackers could often circumvent. DBSC fundamentally changes the web's capability to defend against this threat by shifting the paradigm from reactive detection to proactive prevention, ensuring that successfully exfiltrated cookies cannot be used to access users’ accounts.\n\nHow DBSC Works\n\nDBSC protects against session theft by cryptographically binding authentication sessions to a specific device. It does this using hardware-backed security modules, such as the Trusted Platform Module (TPM) on Windows and the Secure Enclave on macOS, to generate a unique public/private key pair that cannot be exported from the machine. The issuance of new short-lived session cookies is contingent upon Chrome proving possession of the corresponding private key to the server. Because attackers cannot steal this key, any exfiltrated cookies quickly expire and become useless to those attackers. This design allows large and small websites to upgrade to secure, hardware-bound sessions by adding dedicated registration and refresh endpoints to their backends, while maintaining complete compatibility with their existing front-end. The browser handles the complex cryptography and cookie rotation in the background, allowing the web app to continue using standard cookies for access just as it always has.\n\nGoogle rolled out an early version of this protocol over the last year. For sessions protected by DBSC, we have observed a significant reduction in session theft since its launch.\n\nAn overview of the DBSC protocol showing the interaction between the browser and server.\n\nPrivate by design\n\nA core tenet of the DBSC architecture is the preservation of user privacy. Each session is backed by a distinct key, preventing websites from using these credentials to correlate a user's activity across different sessions or sites on the same device. Furthermore, the protocol is designed to be lean: it does not leak device identifiers or attestation data to the server beyond the per-session public key required to certify proof of possession. This minimal information exchange ensures DBSC helps secure sessions without enabling cross-site tracking or acting as a device fingerprinting mechanism.\n\nEngagement with the ecosystem\n\nDBSC was designed from the beginning to be an open web standard through the W3C process and adoption by the Web Application Security Working Group. Through this process we partnered with Microsoft to…","url":"http://security.googleblog.com/2026/04/protecting-cookies-with-device-bound.html","published_at":"2026-04-09T17:07:00Z","updated_at":"2026-04-09T17:11:04Z","fetched_at":"2026-11-21T19:15:07.449277Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"microsoft","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/600","html":"https://vulnwatch.ve1ve2.com/item/600"}},{"id":601,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Google Workspace’s continuous approach to mitigating indirect prompt injections","summary":"Posted by Adam Gavish, Google GenAI Security Team\nIndirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by the LLM as it completes the user’s query. This may even be possible without any input directly from the user.\nIPI is not the kind of technical problem you “solve” and move on. Sophisticated LLMs with increasing use of agentic automation combined with a wide range of content create an ultra-dynamic and evolving playground for adversarial attacks. That’s why Google takes a sophisticated and comprehensive approach to these attacks. We’re continuously improving LLM resistance to IPI attacks and launching AI application capabilities with ever-improving defenses.\nStaying ahead of the latest indirect prompt injection attacks is critical to our mission of securing Workspace with Gemini.\nIn our previous blog “\nMitigating prompt injection attacks with a layered defense strategy\n”, we reviewed the layered architecture of our IPI defenses. In this blog, we’ll share more detail on the continuous approach we take to improve these defenses and to solve for new attacks.\nNew attack discovery\nBy proactively discovering and cataloging new attack vectors through internal and external programs, we can identify vulnerabilities and deploy robust defenses ahead of adversarial activity.\nHuman Red-Teaming\nHuman\nRed-Teaming\nuses adversarial simulations to uncover security and safety vulnerabilities. Specialized teams execute attacks based on realistic user profiles to exploit weaknesses, coordinating with product teams to resolve identified issues.\nAutomated Red-Teaming\nAutomated Red-Teaming is done via dynamic, machine-learning-driven frameworks to stress-test environments. By algorithmically generating and iterating on attack payloads, we can mimic the behavior of sophisticated threats at scale. This allows us to map complex attack paths and validate the effectiveness of our security controls across a much wider range of edge cases than manual testing could achieve on its own.\nGoogle AI Vulnerability Rewards Program (VRP)\nThe\nGoogle AI Vulnerability Rewards Program (VRP)\nis a critical tool for enabling collaboration between Google and external security researchers who discover new attacks leveraging IPI. Through this VRP, we recognize and reward contributors for their research.  We also host regular, live hacking events where we provide invited researchers access to pre-release features, proactively uncovering novel vulnerabilities. These partnerships enable Google to quickly validate, reproduce, and resolve externally-discovered issues.\nPublicly disclosed AI attacks\nGoogle utilizes open-source intelligence feeds to stay on top of the latest publicly disclosed IPI attacks, across social media, press releases, blogs, and more. From there, new AI vulnerabilities are sourced, reproduced, and catalogued internally to ensure our products are not impacted.\nVulnerability catalog\nAll newly discovered vulnerabilities go through a comprehensive analysis process performed by the Google Trust, Security, & Safety teams. Each new vulnerability is reproduced, checked for duplications, mapped into attack technique / impact category, and assigned to relevant owners. The combination of new attack discovery sources and vulnerability catalog process helps Google stay on top of the latest attacks in an actionable manner.\nSynthetic data generation\nAfter we discover, curate, and catalog new attacks, we use\nSimula\nto generate synthetic data expanding these new attacks. This process is essential because it allows the team to develop attack variants for completeness and coverage, and to prepare new training and validation data sets. This accelerated workflow has boosted synthetic data generation by 75%, supporting large-scale defe…","url":"http://security.googleblog.com/2026/04/google-workspaces-continuous-approach.html","published_at":"2026-04-02T16:00:00Z","updated_at":"2026-04-02T19:29:07Z","fetched_at":"2026-11-21T19:15:07.449277Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/601","html":"https://vulnwatch.ve1ve2.com/item/601"}},{"id":602,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"VRP 2025 Year in Review","summary":"Posted by Dirk G\nö\nhmann, Tony Mendez, and the Vulnerability Rewards Program Team\n2025 marked a special year in the history of vulnerability rewards and bug bounty programs at Google: our 15th anniversary 🎉🎉🎉! Originally\nstarted in 2010\n, our vulnerability reward program (VRP) has seen constant additions and expansions over the past decade and a half, clearly indicating the value the programs under this umbrella contribute to the safety and security of Google and its users, but also highlighting their acceptance by the external research community, without which such programs cannot function.\nComing back to 2025 specifically,\nour VRP once again confirmed the ongoing value of engaging with the external security research community to make Google and its products safer. This was more evident than ever as we awarded over $17 million (an all-time high and more than 40% increase compared to 2024!) to over 700 researchers based in countries around the globe – across all of our\nprograms\n.\nVulnerability Reward Program 2025 in Numbers\nWant to learn more about who’s reporting to the VRP? Check out our\nLeaderboard\non the\nGoogle Bug Hunters site\n.\nVRP Highlights in 2025\nIn 2025 we made a series of changes and improvements to our VRP and related initiatives, and continued to invest in the security research community through a series of focused events:\nThe new, dedicated AI VRP was\nlaunched\n, underscoring the importance of this space to Google and its relevance for external researchers. Previously organized as a part of the Abuse VRP, moving into a dedicated VRP has gone hand in hand with improvements to the rules, offering researchers more clarity on scope and reward amounts.\nSimilarly, the Chrome VRP now also includes reward categories for problems found in\nAI features\n.\nWe\nlaunched\na patch rewards program for OSV-SCALIBR, Google's open source tool for finding vulnerabilities in software dependencies. Contributors are rewarded for providing novel OSV-SCALIBR plugins for inventory, vulnerability, or secret detection that expand the tool’s scanning capabilities. Besides strengthening the tool’s capabilities for all users, user submissions already helped us uncover and remediate a number of leaked secrets internally!\nAs part of Google's Cybersecurity Awareness Month campaign in October, we hosted our very own\nsecurity conference in Mexico City, ESCAL8\n. The conference included init.g(mexico), our cybersecurity workshop for students, HACKCELER8, Google’s CTF finals, and a\nSafer with Google\nseminar, sharing technical thought leadership with Mexican government officials.\nbugSWAT,\nour special invite-only live hacking event, saw several editions in 2025 and\n\ndelivered some outstanding findings across different areas:\nWe hosted our first dedicated\nAI bugSWAT (Tokyo) in April\nwhich yielded a whopping 70+ reports filed and over $400,000 in rewards issued.\nWe continued the momentum in early summer with\nCloud bugSWAT (Sunnyvale) in June\nresulting in 130 reports, with $1,600,000 in rewards paid out.\nNext in line was bugSWAT Las Vegas in August, leading to 77 reports and rewards of $380,000.\nAnd finally, as part of ESCAL8 in Mexico City,\nbugSWAT Mexico\nfocused on many different targets and spaces including AI, Android, and Cloud, and resulted in the filing of 107 reports, totalling $566,000 in rewards to date.\nLooking for more details?\nSee the\nextended version of this post\non the Security Engineering blog for reports from individual VRPs such as Android, Abuse, AI, Cloud, Chrome, and OSS, including specifics concerning high-impact bug reports and focus areas of security research.\nWhat’s coming in 2026\nIn 2026, we remain fully committed to fostering collaboration, innovation, and transparency with the security community by hosting several bugSWAT events throughout the year, and following up with the next edition of our cybersecurity conference, ESCAL8. More broadly, our goal remains to stay ahead of emerging threats, adapt to evolving technologies, and co…","url":"http://security.googleblog.com/2026/03/vrp-2025-year-in-review.html","published_at":"2026-03-31T16:55:00Z","updated_at":"2026-03-31T16:55:35Z","fetched_at":"2026-11-21T19:15:07.449278Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/602","html":"https://vulnwatch.ve1ve2.com/item/602"}},{"id":603,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Security for the Quantum Era: Implementing Post-Quantum Cryptography in Android","summary":"Posted by Eric Lynch, Product Manager, Android and Dom Elliott, Group Product Manager, Google Play\n\nModern digital security is at a turning point.\nWe are on the threshold of using quantum computers to solve \"impossible\" problems\nin drug discovery, materials science, and energy—tasks that even the most powerful classical supercomputers cannot handle. However, the same unique ability to consider different options simultaneously also allows these machines to bypass our current digital locks. This puts the public-key cryptography we’ve relied on for decades at risk, potentially compromising everything from bank transfers to trade secrets. To secure our future, it is vital to adopt the new Post-Quantum Cryptography (PQC) standards National Institute of Standards and Technology (NIST) is urging before large-scale, fault-tolerant quantum computers become a reality.\n\nTo stay ahead of the curve, the technology industry must undertake a proactive, multi-year migration to Post-Quantum Cryptography (PQC). We have been\npreparing for a post-quantum world since 2016\n, conducting pioneering experiments with post-quantum cryptography, rolling out post-quantum capabilities in our products, and sharing our expertise through threat models and technical papers. For Android, the objective extends beyond patching individual applications or transport protocols. The imperative is to ensure that the entire platform architecture is resilient for the decades to come.\n\nWe are beginning tests of PQC enhancements starting in the next Android 17 beta, followed by general availability in the Android 17 production release. This deployment introduces a comprehensive architectural upgrade that is being rolled out across the operating system. By integrating the recently finalized\nNIST PQC standards\ndeep into the platform, we’re establishing a new, quantum-resistant chain of trust. This chain of trust secures the platform continuously—from the moment the OS powers on, to the execution of applications distributed globally. Android is swapping today’s digital locks for advanced encryption to help enhance the security of every app you download—no matter how powerful future supercomputers get.\n\nSecuring the foundation: Verified boot and hardware trust\n\nSecurity on any computing device begins when the hardware starts; if the underlying operating system is compromised, all subsequent software protections fail. As quantum computing advances, adversaries could potentially forge digital signatures to bypass these foundational integrity checks. To secure the platform against this looming threat, Android 17 introduces two major post-quantum cryptographic (PQC) upgrades:\n\nUpgrading Android Verified Boot (AVB):\nThe AVB library is integrating the Module-Lattice-Based Digital Signature Algorithm (ML-DSA). This provides quantum-resistant digital signatures, ensuring the software loaded during the boot sequence remains highly resistant to unauthorized modification.\n\nMigrating Remote Attestation:\nAndroid 17 begins the transition of Remote Attestation to a fully PQC-compliant architecture under the current standards. By updating KeyMint's certificate chains to support quantum-resistant algorithms, devices can securely prove their state to relying parties, maintaining trust in a post-quantum environment.\n\nEmpowering developers: Android Keystore updates\n\nProtecting the underlying operating system is only the first layer of defense; developers must be equipped with the cryptographic primitives necessary to leverage PQC keys and establish robust identity verification.\n\nImplementing lattice-based cryptography, which requires significantly larger key sizes and memory footprints than classical elliptic curve cryptography, within the severely resource-constrained Trusted Execution Environment (TEE), represents a major engineering achievement. This capability is designed to support the hardware roots of trust and can now generate and verify post-quantum signatures.\n\nBuilding on this hardwar…","url":"http://security.googleblog.com/2026/03/post-quantum-cryptography-in-android.html","published_at":"2026-03-25T13:00:00Z","updated_at":"2026-03-30T15:11:01Z","fetched_at":"2026-11-21T19:15:07.449279Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/603","html":"https://vulnwatch.ve1ve2.com/item/603"}},{"id":604,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Cultivating a robust and efficient quantum-safe HTTPS","summary":"Posted by Chrome Secure Web and Networking Team\n\nToday we're announcing a new program in Chrome to make HTTPS certificates secure against quantum computers. The Internet Engineering Task Force (IETF) recently created a working group,\nPKI, Logs, And Tree Signatures\n(“PLANTS”), aiming to address the performance and bandwidth challenges that the increased size of\nquantum-resistant cryptography\nintroduces into TLS connections requiring\nCertificate Transparency\n(CT). We recently\nshared\nour call to action to secure quantum computing and have written about challenges introduced by quantum-resistant cryptography and some of the steps we’ve taken to address them in earlier\nblog\n\nposts\n.\n\nTo ensure the scalability and efficiency of the ecosystem, Chrome has no immediate plan to add traditional X.509 certificates containing post-quantum cryptography to the\nChrome Root Store\n. Instead, Chrome, in collaboration with other partners, is developing an\nevolution\nof HTTPS certificates based on\nMerkle Tree Certificates\n(MTCs), currently in development in the PLANTS working group. MTCs replace the heavy, serialized chain of signatures found in traditional PKI with compact\nMerkle Tree proofs\n. In this model, a Certification Authority (CA) signs a single \"Tree Head\" representing potentially millions of certificates, and the \"certificate\" sent to the browser is merely a lightweight proof of inclusion in that tree.\n\nWhy MTCs?\n\nMTCs enable the adoption of robust post-quantum algorithms without incurring the massive bandwidth penalty of classical X.509 certificate chains. They also decouple the security strength of the corresponding cryptographic algorithm from the size of the data transmitted to the user. By shrinking the authentication data in a TLS handshake to the absolute minimum, MTCs aim to keep the post-quantum web as fast and seamless as today’s internet, maintaining high performance even as we adopt stronger security. Finally, with MTCs, transparency is a fundamental property of issuance: it is impossible to issue a certificate without including it in a public tree. This means the security properties of today’s CT ecosystem are included by default, and without adding extra overhead to the TLS handshake as CT does today.\n\nChrome’s MTC Propagation Plan\n\nChrome is already experimenting with MTCs with real internet traffic, and we intend to gradually build out our deployment such that MTCs provide a robust quantum-resistant HTTPS available for use throughout the internet.\n\nBroadly speaking, our rollout spans three distinct phases.\n\nPhase 1 (UNDERWAY):\nIn\ncollaboration\nwith Cloudflare, we are conducting a feasibility study to evaluate the performance and security of TLS connections relying on MTCs. To ensure a seamless and secure experience for Chrome users who might encounter an MTC, every MTC-based connection is backed by a traditional, trusted X.509 certificate during this experiment. This \"fail safe\" allows us to measure real-world performance gains and verify the reliability of MTC issuance without risking the security or stability of the user's connection.\n\nPhase 2 (Q1 2027):\nOnce the core technology is validated, we intend to invite CT Log\noperators\nwith at least one “\nusable\n” log in Chrome before February 1, 2026 to participate in the initial bootstrapping of public MTCs. These organizations have already demonstrated the operational excellence and high-availability infrastructure required to run global security services that underpin TLS connections in Chrome. Since MTC technology shares significant architectural similarities with CT, these operators are uniquely qualified to ensure MTCs are able to get off the ground quickly and successfully.\n\nPhase 3 (Q3 2027):\nEarly in Phase 2, we will finalize the requirements for onboarding additional CAs into the new Chrome Quantum-resistant Root Store (CQRS) and corresponding Root Program that only supports MTCs. This will establish a modern, purpose-built trust store specifically designed for the…","url":"http://security.googleblog.com/2026/02/cultivating-robust-and-efficient.html","published_at":"2026-02-27T17:01:00Z","updated_at":"2026-02-27T17:01:27Z","fetched_at":"2026-11-21T19:15:07.449279Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/604","html":"https://vulnwatch.ve1ve2.com/item/604"}},{"id":605,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Staying One Step Ahead: Strengthening Android’s Lead in Scam Protection","summary":"Posted by Lyubov Farafonova, Product Manager, Phone by Google; Alberto Pastor Nieto, Sr. Product Manager Google Messages and RCS Spam and Abuse\n\nWe’ve\nshared\nhow Android’s proactive, multi-layered scam defenses utilize Google AI to protect users around the world from over 10 billion suspected malicious calls and messages every month\n1\n. While that scale is significant, the true impact of these protections is best understood through the stories of the individuals they help keep safe every day. This includes people like Majik B., an IT professional in Sunnyvale, California.\n\nDespite his technical background, Majik recently found himself on a call that felt dangerously legitimate. While using his Pixel, he received a call that appeared to be from his bank. The number looked correct, the caller knew his name and his address, and the story about a \"suspicious charge\" made perfect sense. \"I’m usually pretty careful about this stuff,\" Majik recalled, \"but I stayed on the line longer than I normally would. Even knowing how these scams work, it was convincing in the moment.\"\n\nThe turning point came when his phone displayed a Scam Detection warning during the call, which provided a critical moment to pause and reflect. Majik hung up, checked his bank app directly, and confirmed there was no fraudulent charge. For Majik, Scam Detection was the intervention he needed: “The warning is what made me pause and avoid a bad situation”.\n\nWhile stories like Majik’s show how our existing protections provide a robust shield against scams, our work isn't done. As scammers evolve their tactics and create more convincing and personalized threats, we’re using the best of Google AI to stay one step ahead.\n\nA recent\nevaluation\nby\nCounterpoint Research\nfound that Android smartphones provide the most comprehensive AI-powered protections of any mobile platform. We are committed to building on this foundation by expanding our AI-powered protections to more users and devices, while rolling out new features that utilize on-device AI to defend against increasingly sophisticated threats.\n\nExpanding Scam Detection for Calls to Samsung Devices\n\nTo help protect you during phone calls, Scam Detection alerts you if a caller uses speech patterns commonly associated with fraud. We are bringing these protections to more of our users through new regional expansion and availability on new devices. Scam Detection for phone calls on Google Pixel devices is available in the US, UK, Australia, Canada, France, Germany, India, Ireland, Italy, Japan, Mexico, and Spain.\n\nScam Detection is already helping millions of users to stay safe from scammers, and we are expanding this feature to more manufacturers, starting with the Samsung Galaxy S26 series in the U.S. We are continuing to work with our partners to bring these industry-leading protections to even more users.\n\nPowered by Gemini’s on-device model, Scam Detection provides intelligent protection against scam calls while ensuring that the processing stays on your device. This keeps your conversations private while delivering warnings in real-time. To preserve your privacy, the phone conversation processed by Scam Detection is neither stored on your device, nor shared outside of the device. To ensure you stay in total control of your experience, Scam Detection is turned off by default. When enabled, the feature only applies to calls identified as potential scams and is never used in calls with your contacts. You can easily manage these preferences in your phone settings whenever you choose.\n\nEnhanced Protection Against Messaging Scams\n\nWe want everyone to feel secure when they open their messages, no matter where they are or what language they speak. To make this possible, we’ve now expanded Scam Detection for Google Messages to more than 20 countries. This includes support for several languages including English, Arabic, French, German, Portuguese, and Spanish.\n\nBeyond reaching more people, we are also making our protections…","url":"http://security.googleblog.com/2026/02/strengthening-android-lead-in-scam-protection.html","published_at":"2026-02-25T15:17:00Z","updated_at":"2026-03-18T18:53:00Z","fetched_at":"2026-11-21T19:15:07.449280Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/605","html":"https://vulnwatch.ve1ve2.com/item/605"}},{"id":606,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Keeping Google Play & Android app ecosystems safe in 2025","summary":"Posted by Vijaya Kaza, VP and GM, App & Ecosystem Trust\n\nThe Android ecosystem is a thriving global community built on trust, giving billions of users the confidence to download the latest apps. In order to maintain that trust, we’re focused on ensuring that apps do not cause real-world harm, such as malware, financial fraud, hidden subscriptions, and privacy invasions. As bad actors leverage AI to change their tactics and launch increasingly sophisticated attacks, we’ve deepened our investments in AI and real-time defenses over the last year to maintain the upper hand and stop these threats before they reach users.\n\nUpgrading Google Play’s AI-powered, multi-layered user protections\n\nWe’ve seen a clear impact from these safety efforts on Google Play. In 2025,\nwe prevented over 1.75 million policy-violating apps from being published on Google Play\nand\nbanned more than 80,000 bad developer accounts that attempted to publish harmful apps.\nThese figures demonstrate how our proactive protections and push for a more accountable ecosystem are discouraging bad actors from publishing malicious apps, while our new tools help honest developers build compliant apps more easily. Initiatives like developer verification, mandatory pre-review checks, and testing requirements have raised the bar for the Google Play ecosystem, significantly reducing the paths for bad actors to enter.\n\nUser safety is at the core of everything we build. Over the years, we’ve continually introduced ways to help users stay safe and make informed app choices — from\nparental controls\nto\ndata safety transparency\nand\napp badges\n. We’re constantly improving our policies and protections to encourage safe, high-quality apps on Google Play and stop bad actors before they cause harm.\n\nApps on Google Play undergo rigorous reviews for safety and compliance with our policies. Last year,\nwe shared\nthat Google Play runs\nover 10,000 safety checks\non every app we publish, and we continue to check and recheck apps after they’ve been published. In 2025, we continued scaling our defenses even further by:\n\nBoosting AI-enhanced app detection\n: We integrated Google’s latest generative AI models into our review process, helping our human review team continue to find complex malicious patterns faster.\n\nPreventing unnecessary access to sensitive data:\nWe prevented\nover 255,000 apps\nfrom getting excessive access to sensitive user data and continued to strengthen our privacy policies. Our commitment to privacy-forward app development, supported by tools like Play Policy Insights in\nAndroid Studio\nand\nData safety section\n, has empowered developers to continue to: minimize privacy-sensitive permission requests, and prioritize the user in their design choices.\n\nBlocking spam ratings and reviews:\nWhether they lead to review inflation or deflation, spam ratings and reviews can negatively impact our users’ trust and our developers’ growth. We’re continually evolving our detection models to help ensure app reviews are accurate. Our anti-spam protections blocked\n160 million spam ratings and reviews\nlast year, including inflated and deflated reviews. We also\nprevented an average 0.5-star rating drop\nfor apps targeted by review bombing, protecting our users and developers from unhelpful reviews.\n\nSafeguarding kids and families\n: Our approach to kids and families is built on the core belief that children deserve a safe, enriching digital environment. Our commitment is to empower parents with robust tools while providing children with access to high-quality, age-appropriate content. Last year, we announced\nnew layers of protection\n, in addition to our existing\nsafeguards\n, to prevent younger audiences from discovering or downloading apps involving activities like gambling or dating.\n\nEnhancing Google Play Protect to help keep the entire Android ecosystem safe\n\nWe also continued to improve our protections for the broader Android ecosystem, by expanding\nGoogle Play Protect\nand real-time security measures…","url":"http://security.googleblog.com/2026/02/keeping-google-play-android-app-ecosystem-safe-2025.html","published_at":"2026-02-19T17:00:00Z","updated_at":"2026-02-19T17:00:19Z","fetched_at":"2026-11-21T19:15:07.449281Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security","google play","google play protect"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/606","html":"https://vulnwatch.ve1ve2.com/item/606"}},{"id":607,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"New Android Theft Protection Feature Updates: Smarter, Stronger","summary":"Posted by Nataliya Stanetsky, Fabricio Ferracioli, Elliot Sisteron, Irene Ang of the Android Security Team\n\nPhone theft is more than just losing a device; it's a form of financial fraud that can leave you suddenly vulnerable to personal data and financial theft. That’s why we're committed to providing multi-layered defenses that help protect you before, during, and after a theft attempt.\n\nToday, we're announcing a powerful set of theft protection feature updates that build on our\nexisting protections\n, designed to give you greater peace of mind by making your device a much harder target for criminals.\n\nStronger Authentication Safeguards\n\nWe've expanded our security to protect you against an even wider range of threats. These updates are now available for Android devices running Android 16+.\n\nMore User Control for Failed Authentications:\nIn Android 15,\nwe launched\nFailed Authentication Lock, a feature that automatically locks the device's screen after excessive failed authentication attempts. This feature is now getting a new dedicated enable/disable toggle in settings, giving you more granular control over your device's security.\n\nExpanding Identity Check to cover more:\nEarly in 2025\n, we enabled Identity Check for Android 15+, which requires the user to utilize biometrics when performing certain actions outside of trusted places. Later in the year, we extended this safeguard to cover all features and apps that use the Android Biometric Prompt. This means that critical tools that utilize Biometric Prompt, like third-party banking apps and Google Password Manager, now automatically benefit from the additional security of Identity Check.\n\nStronger Protection Against Screen Lock Guessing:\nWe’re making it much harder for a thief to guess your PIN, pattern, or password by increasing the lockout time after failed attempts. To ensure you aren’t locked out by mistake (\nby a curious child\n, for instance), identical incorrect guesses no longer count toward your retry limit.\n\nEnhanced Recovery Tools\n\nWe're also enhancing our recovery tools to make them even more helpful. This update is now available for Android devices running Android 10+.\n\nMore Control for Remote Lock.\nRemote Lock (\nandroid.com/lock\n) is a crucial tool that lets you lock your lost or stolen device from any web browser. We are adding a new optional security question/challenge to the process. This helps ensure that only you, the real device owner, can initiate a lock, adding another layer of security to your recovery flow.\n\nProactive Protection: \"Default-On\" in Brazil\n\nKeeping our users safe is a top priority, which is why we're working to make theft protection available out-of-the-box for more Android users. For new Android devices activated in Brazil, two of our key\ntheft protection features\nare now enabled by default:\n\nTheft Detection Lock:\nUses on-device AI to sense motion and context that may indicate a \"snatch-and-run\" theft. If a theft attempt is detected, it will quickly lock the device screen to help protect your data.\n\nRemote Lock:\nAllows users to lock their device from any device that provides a web access to\nandroid.com/lock\nwithout the need to have enabled the feature in advance.\n\nThis helps ensure new devices have a critical layer of theft protection from day one.\n\nContinuing To innovate in Device Theft Protection\n\nWe’re always evolving our protections to stay one step ahead of thieves. Our ongoing updates help ensure that no matter where you go, you can have greater peace of mind knowing your device and data are protected by Android’s multi-layered defenses. Keep a lookout for even more Android theft protection updates.","url":"http://security.googleblog.com/2026/01/android-theft-protection-feature-updates.html","published_at":"2026-01-27T16:59:00Z","updated_at":"2026-01-27T16:59:53Z","fetched_at":"2026-11-21T19:15:07.449281Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/607","html":"https://vulnwatch.ve1ve2.com/item/607"}},{"id":608,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"HTTPS certificate industry phasing out less secure domain validation methods","summary":"Posted by Chrome Root Program Team\n\nSecure connections are the backbone of the modern web, but a certificate is only as trustworthy as the validation process and issuance practices behind it. Recently, the\nChrome Root Program\nand the\nCA/Browser Forum\nhave taken decisive steps toward a more secure internet by adopting new security requirements for HTTPS certificate issuers.\n\nThese initiatives, driven by Ballots\nSC-080\n,\nSC-090\n, and\nSC-091\n, will sunset 11 legacy methods for Domain Control Validation. By retiring these outdated practices, which rely on weaker verification signals like physical mail, phone calls, or emails, we are closing potential loopholes for attackers and pushing the ecosystem toward automated, cryptographically verifiable security.\n\nTo allow affected website operators to transition smoothly, the deprecation will be phased in, with its full security value realized by March 2028.\n\nThis effort is a key part of our public roadmap, “\nMoving Forward, Together,\n” launched in 2022. Our vision is to improve security by modernizing infrastructure and promoting agility through automation. While \"Moving Forward, Together\" sets the aspirational direction, the recent updates to the\nTLS Baseline Requirements\nturn that vision into policy. This builds on our momentum from earlier this year, including the successful\nadvocacy for the adoption of other security enhancing initiatives\nas industry-wide standards.\n\nWhat’s Domain Control Validation?\n\nDomain Control Validation is a security-critical process designed to ensure certificates are only issued to the legitimate domain operator. This prevents unauthorized entities from obtaining a certificate for a domain they do not control. Without this check, an attacker could obtain a valid certificate for a legitimate website and use it to impersonate that site or intercept web traffic.\n\nBefore issuing a certificate, a Certification Authority (CA) must verify that the requestor legitimately controls the domain. Most modern validation relies on “challenge-response” mechanisms, for example, a CA might provide a random value for the requestor to place in a specific location, like a DNS TXT record, which the CA then verifies.\n\nHistorically, other methods validated control through indirect means, such as looking up contact information in WHOIS records or sending an email to a domain contact. These methods have been proven vulnerable (\nexample\n) and the recent efforts retire these weaker checks in favor of robust, automated alternatives.\n\nRaising the floor of security\n\nThe recently passed CA/Browser Forum Server Certificate Working Group Ballots introduce a phased sunset of the following Domain Control Validation methods. Alternative existing methods offer stronger security assurances against attackers trying to obtain fraudulent certificates – and the alternative methods are getting\nstronger\nover time, too.\n\nSunsetted methods relying on email:\n\nEmail, Fax, SMS, or Postal Mail to Domain Contact\n\nEmail, Fax, SMS, or Postal Mail to IP Address Contact\n\nConstructed Email to Domain Contact\n\nEmail to DNS CAA Contact\n\nEmail to DNS TXT Contact\n\nSunsetted methods relying on phone:\n\nPhone Contact with Domain Contact\n\nPhone Contact with DNS TXT Record Phone Contact\n\nPhone Contact with DNS CAA Phone Contact\n\nPhone Contact with IP Address Contact\n\nSunsetted method relying on a reverse lookup:\n\nIP Address\n\nReverse Address Lookup\n\nFor everyday users, these changes are invisible - and that’s the point. But, behind the scenes, they make it harder for attackers to trick a CA into issuing a certificate for a domain they don’t control. This reduces the risk that stale or indirect signals, (like outdated WHOIS data, complex phone and email ecosystems, or inherited infrastructure) can be abused. These changes push the ecosystem toward standardized (e.g.,\nACME\n), modern, and auditable Domain Control Validation methods. They increase agility and resilience by encouraging site owners to transition to modern Domain…","url":"http://security.googleblog.com/2025/12/https-certificate-industry-phasing-out.html","published_at":"2025-12-10T20:00:00Z","updated_at":"2025-12-10T20:00:22Z","fetched_at":"2026-11-21T19:15:07.449282Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/608","html":"https://vulnwatch.ve1ve2.com/item/608"}},{"id":609,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Further Hardening Android GPUs","summary":"Posted by Liz Prucka, Hamzeh Zawawy, Rishika Hooda, Android Security and Privacy Team\n\nLast year, Google's Android Red Team partnered with Arm to conduct an\nin-depth security analysis\nof the Mali GPU, a component used in billions of Android devices worldwide. This collaboration was a significant step in proactively identifying and fixing vulnerabilities in the GPU software and firmware stack.\n\nWhile finding and fixing individual bugs is crucial, and\nprogress continues on eliminating them entirely\n, making them unreachable by restricting attack surface is another effective and often faster way to improve security. This post details our efforts in partnership with Arm to further harden the GPU by reducing the driver's attack surface.\n\nThe Growing Threat: Why GPU Security Matters\n\nThe Graphics Processing Unit (GPU) has become a critical and attractive target for attackers due to its complexity and privileged access to the system. The scale of this threat is significant: since 2021, the majority of Android kernel driver-based\nexploits\nhave targeted the GPU. These exploits primarily target the interface between the User-Mode Driver (UMD) and the highly privileged Kernel-Mode Driver (KMD), where flaws can be exploited by malicious input to trigger memory corruption.\n\nPartnership with Arm\n\nOur goal is to raise the bar on GPU security, ensuring the Mali GPU driver and firmware remain highly resilient against potential threats. We partnered with Arm to conduct an analysis of the Mali driver, used on approximately 45% of Android devices. This collaboration was crucial for understanding the driver’s attack surface and identifying areas that posed a security risk, but were not necessary for production use.\n\nThe Right Tool for the Job: Hardening with SELinux\n\nOne of the key findings of our investigation was the opportunity to restrict access to certain GPU IOCTLs. IOCTLs act as the GPU kernel driver’s user input and output, as well as the attack surface. This approach builds on earlier kernel hardening efforts, such as those described in the 2016 post\nProtecting Android with More Linux Security\n. Mali ioctls can be broadly categorized as:\n\nUnprivileged: Necessary for normal operation.\n\nInstrumentation: Used by developers for profiling and debugging.\n\nRestricted: Should not be used by applications in production. This includes IOCTLs which are intended only for GPU development, as well as IOCTLs which have been deprecated and are no longer used by a device’s current User-Mode Driver (UMD) version.\n\nOur goal is to block access to deprecated and debug IOCTLs in production. Instrumentation IOCTLs are intended for use by profiling tools to monitor system GPU performance and are not intended to be directly used by applications in production. As such, access is restricted to\nshell\nor applications marked as\ndebuggable\n. Production IOCTLs remain accessible to regular applications.\n\nA Staged Rollout\n\nThe approach is iterative and is a staged rollout for devices using the Mali GPU. This way, we were able to carefully monitor real-world usage and collect data to validate the policy, minimizing the risk of breaking legitimate applications before moving to broader adoption:\n\nOpt-In Policy: We started with an \"opt-in\" policy. We created a new SELinux attribute,\ngpu_harden\n, that disallowed instrumentation ioctls. We then selectively applied this attribute to certain system apps to test the impact. We used the\nallowxperm\nrule to audit, but not deny, access to the intended resource, and monitored the denial logs to ensure no breakage.\n\nOpt-Out Policy: Once we were confident that our approach was sound, we moved to an \"opt-out\" policy. We created a\ngpu_debug\ndomain that would allow access to instrumentation ioctls. All applications were hardened by default, but developers could opt-out by:\n\nRunning on a rooted device.\n\nSetting the\nandroid:debuggable=\"true\"\nattribute in their app's manifest.\n\nRequesting a permanent exception in the SELinux policy for their a…","url":"http://security.googleblog.com/2025/12/further-hardening-android-gpus.html","published_at":"2025-12-09T17:00:00Z","updated_at":"2025-12-09T17:20:33Z","fetched_at":"2026-11-21T19:15:07.449283Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/609","html":"https://vulnwatch.ve1ve2.com/item/609"}},{"id":610,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Architecting Security for Agentic Capabilities in Chrome","summary":"Posted by Nathan Parker, Chrome security team\n\nChrome has been advancing the web’s security for well over 15 years, and we’re committed to meeting new challenges and opportunities with AI. Billions of people trust Chrome to keep them safe by default, and this is a responsibility we take seriously. Following the\nrecent launch of Gemini in Chrome\nand the\npreview of agentic capabilities\n, we want to share our approach and some new innovations to improve the safety of agentic browsing.\n\nThe primary new threat facing all agentic browsers is\nindirect prompt injection\n. It can appear in malicious sites, third-party content in iframes, or from user-generated content like user reviews, and can cause the agent to take unwanted actions such as initiating financial transactions or exfiltrating sensitive data. Given this open challenge, we are investing in a\nlayered defense\nthat includes both deterministic and probabilistic defenses to make it difficult and costly for attackers to cause harm.\n\nDesigning safe agentic browsing for Chrome has involved deep collaboration of security experts across Google. We built on Gemini's\nexisting protections\nand\nagent security principles\nand have implemented several new layers for Chrome.\n\nWe’re introducing a\nuser alignment critic\nwhere the agent’s actions are vetted by a separate model that is isolated from untrusted content. We’re also extending Chrome’s\norigin-isolation capabilities\nto constrain what origins the agent can interact with, to just those that are relevant to the task. Our layered defense also includes\nuser confirmations\nfor critical steps,\nreal-time detection of threats\n, and\nred-teaming and response\n. We’ll step through these layers below.\n\nChecking agent outputs with User Alignment Critic\n\nThe main planning model for Gemini uses page content shared in Chrome to decide what action to take next. Exposure to untrusted web content means it is inherently vulnerable to indirect prompt injection. We use techniques like\nspotlighting\nthat direct the model to strongly prefer following user and system instructions over what’s on the page, and we’ve upstreamed known attacks to train the Gemini model to avoid falling for them.\n\nTo further bolster model alignment beyond spotlighting, we’re introducing the\nUser Alignment Critic\n— a separate model built with Gemini that acts as a high-trust system component. This architecture is inspired partially by the\ndual-LLM pattern\nas well as\nCaMeL research\nfrom Google DeepMind.\n\nA flow chart that depicts the User Alignment Critic: a trusted component that vets each action before it reaches the browser.\n\nThe User Alignment Critic runs after the planning is complete to double-check each proposed action. Its primary focus is task alignment: determining whether the proposed action serves the user’s stated goal. If the action is misaligned, the Alignment Critic will veto it. This component is architected to see only metadata about the proposed action and not any unfiltered untrustworthy web content, thus ensuring it cannot be poisoned directly from the web. It has less context, but it also has a simpler job — just approve or reject an action.\n\nThis is a powerful, extra layer of defense against both goal-hijacking and data exfiltration within the action step. When an action is rejected, the Critic provides feedback to the planning model to re-formulate its plan, and the planner can return control to the user if there are repeated failures.\n\nEnforcing stronger security\nbound\naries with Origin Sets\n\nSite Isolation\nand the\nsame-origin policy\nare fundamental boundaries in Chrome’s security model and we’re carrying forward these concepts into the agentic world. By their nature, agents must operate across websites (e.g. collecting ingredients on one site and filling a shopping cart on another). But if an unrestricted agent is compromised and can interact with arbitrary sites, it can create what is effectively a Site Isolation bypass. That can have a severe impact when the a…","url":"http://security.googleblog.com/2025/12/architecting-security-for-agentic.html","published_at":"2025-12-08T18:03:00Z","updated_at":"2025-12-08T19:39:36Z","fetched_at":"2026-11-21T19:15:07.449284Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["chrome","chrome security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/610","html":"https://vulnwatch.ve1ve2.com/item/610"}},{"id":611,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Android expands pilot for in-call scam protection for financial apps","summary":"Posted by Aden Haussmann, Associate Product Manager and Sumeet Sharma, Play Partnerships Trust & Safety Lead\n\nAndroid uses the best of Google AI and our advanced security expertise to tackle mobile scams from every angle. Over the last few years, we’ve launched industry-leading features to detect scams and protect users across\nphone calls, text messages\nand\nmessaging app chat notifications\n.\n\nThese efforts are making a real difference in the lives of Android users. According to a recent YouGov\nsurvey\n1\ncommissioned by Google, Android users were 58% more likely than iOS users to report they had not received any scam texts in the prior week\n2\n.\n\nBut our work doesn’t stop there. Scammers are continuously evolving, using more sophisticated social engineering tactics to trick users into sharing their phone screen while on the phone to visit malicious websites, reveal sensitive information, send funds or download harmful apps. One popular scam involves criminals impersonating banks or other trusted institutions on the phone to try to manipulate victims into sharing their screen in order to reveal banking information or make a financial transfer.\n\nTo help combat these types of financial scams, we\nlaunched a pilot earlier this year in the UK\nfocused on in-call protections for financial apps.\n\nHow the in-call scam protection works on Android\n\nWhen you launch a participating financial app while screen sharing and on a phone call with a number that is not saved in your contacts, your Android device\n3\nwill automatically warn you about the potential dangers and give you the option to end the call and to stop screen sharing with just one tap. The warning includes a 30-second pause period before you’re able to continue, which helps break the ‘spell’ of the scammer's social engineering, disrupting the false sense of urgency and panic commonly used to manipulate you into a scam.\n\nBringing in-call scam protections to more users on Android\n\nThe UK pilot of Android’s in-call scam protections has already helped thousands of users end calls that could have cost them a significant amount of money. Following this success, and alongside recently launched pilots with financial apps in\nBrazil\nand\nIndia\n, we’ve now expanded this protection to most major UK banks.\n\nWe’ve also started to pilot this protection with more app types, including peer-to-peer (P2P) payment apps. Today, we’re taking the next step in our expansion by rolling out a pilot of this protection in the United States\n4\nwith a number of popular fintechs like Cash App and banks, including JPMorganChase.\nWe are committed to collaborating across the ecosystem to help keep people safe from scams. We look forward to learning from these pilots and bringing these critical safeguards to even more users in the future.\n\nNotes\n\nGoogle/YouGov survey, July-August, n=5,100 (1,700 each in the US, Brazil and India), with adults who use their smartphones daily and who have been exposed to a scam or fraud attempt on their smartphone. Survey data have been weighted to smartphone population adults in each country.\n\n↩\n\nAmong users who use the default texting app on their smartphone.\n\n↩\n\nCompatible with Android 11+ devices\n\n↩\n\nUS users of the US versions of the apps; rollout begins Dec. 2025\n\n↩","url":"http://security.googleblog.com/2025/12/android-expands-pilot-in-call-scam-protection-financial-apps.html","published_at":"2025-12-03T16:59:00Z","updated_at":"2025-12-03T16:59:52Z","fetched_at":"2026-11-21T19:15:07.449284Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/611","html":"https://vulnwatch.ve1ve2.com/item/611"}},{"id":612,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Android Quick Share Support for AirDrop: A Secure Approach to Cross-Platform File Sharing","summary":"Posted by Dave Kleidermacher, VP, Platforms Security & Privacy, Google\n\nTechnology should bring people closer together, not create walls. Being able to communicate and connect with friends and family should be easy regardless of the phone they use. That’s why Android has been building experiences that help you stay connected across platforms.\n\nAs part of our efforts to continue to make cross-platform communication more seamless for users, we've made Quick Share interoperable with AirDrop, allowing for two-way file sharing between Android and iOS devices, starting with the Pixel 10 Family. This new feature makes it possible to quickly share your photos, videos, and files with people you choose to communicate with, without worrying about the kind of phone they use.\n\nMost importantly, when you share personal files and content, you need to trust that it stays secure. You can share across devices with confidence knowing we built this feature with security at its core, protecting your data with strong safeguards that have been tested by independent security experts.\n\nSecure by Design\n\nWe built Quick Share’s interoperability support for AirDrop with the same rigorous security standards that we apply to all Google products. Our approach to security is proactive and deeply integrated into every stage of the development process. This includes:\n\nThreat Modeling:\nWe identify and address potential security risks before they can become a problem.\n\nInternal Security Design and Privacy Reviews:\nOur dedicated security and privacy teams thoroughly review the design to ensure it meets our high standards.\n\nInternal Penetration Testing:\nWe conduct extensive in-house testing to identify and fix vulnerabilities.\n\nThis\nSecure by Design\nphilosophy ensures that all of our products are not just functional but also fundamentally secure.\n\nThis feature is also protected by a multi-layered security approach to ensure a safe sharing experience from end-to-end, regardless of what platform you’re on.\n\nSecure Sharing Channel:\nThe communication channel itself is hardened by our use of Rust to develop this feature. This memory-safe language is the industry benchmark for building secure systems and provides confidence that the connection is protected against buffer overflow attacks and other common vulnerabilities.\n\nBuilt-in Platform Protections:\nThis feature is strengthened by the robust built-in security of both Android and iOS. On Android, security is built in at every layer. Our deep investment in Rust at the OS level hardens the foundation, while proactive defenses like\nGoogle Play Protect\nwork to keep your device safe. This is complemented by the security architecture of iOS that provides its own strong safeguards that mitigate malicious files and exploitation. These overlapping protections on both platforms work in concert with the secure connection to provide comprehensive safety for your data when you share or receive.\n\nYou’re in Control:\nSharing across platforms works just like you're used to: a file requires your approval before being received, so you're in control of what you accept.\n\nThe Power of Rust: A Foundation of Secure Communication\n\nA key element of our security strategy for the interoperability layer between Quick Share and AirDrop is the use of the memory-safe Rust programming language. Recognized by security agencies around the world, including the\nNSA\nand\nCISA\n, Rust is widely considered the industry benchmark for building secure systems because it eliminates entire classes of memory-safety vulnerabilities by design.\n\nRust is already a cornerstone\nof our broader initiative to eliminate memory safety bugs across Android. Its selection for this feature was deliberate, driven by the unique security challenges of cross-platform communication that demanded the most robust protections for memory safety.\n\nThe core of this feature involves receiving and parsing data sent over a wireless protocol from another device. Historically, when using a memo…","url":"http://security.googleblog.com/2025/11/android-quick-share-support-for-airdrop-security.html","published_at":"2025-11-20T17:00:00Z","updated_at":"2025-11-20T22:25:07Z","fetched_at":"2026-11-21T19:15:07.449285Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/612","html":"https://vulnwatch.ve1ve2.com/item/612"}},{"id":613,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Rust in Android: move fast and fix things","summary":"Posted by Jeff Vander Stoep, Android\n\nLast year, we wrote\nabout why a memory safety strategy that focuses on vulnerability prevention in new code quickly yields durable and compounding gains. This year we look at how\nthis approach isn’t just fixing things, but helping us move faster\n.\n\nThe 2025 data continues to validate the approach, with memory safety vulnerabilities falling below 20% of total vulnerabilities for the first time.\n\nUpdated data for 2025. This data covers first-party and third-party (open source) code changes to the Android platform across C, C++, Java, Kotlin, and Rust. This post is published a couple of months before the end of 2025, but Android’s industry-standard 90-day patch window means that these results are very likely close to final. We can and will accelerate patching when necessary.\n\nWe adopted Rust for its security and are seeing\na 1000x reduction in memory safety vulnerability density compared to Android’s C and C++ code\n. But the biggest surprise was Rust's impact on software delivery. With Rust changes having\na 4x lower rollback rate\nand spending\n25% less time in code review\n, the safer path is now also the faster one.\n\nIn this post, we dig into the data behind this shift and also cover:\n\nHow we’re expanding our reach:\nWe're pushing to make secure code the default across our entire software stack. We have updates on Rust adoption in first-party apps, the Linux kernel, and firmware.\n\nOur first rust memory safety vulnerability...almost:\nWe'll analyze a near-miss memory safety bug in unsafe Rust: how it happened, how it was mitigated, and steps we're taking to prevent recurrence. It’s also a good chance to answer the question “if Rust can have memory safety issues, why bother at all?”\n\nBuilding Better Software, Faster\n\nDeveloping an operating system requires the low-level control and predictability of systems programming languages like C, C++, and Rust. While Java and Kotlin are important for Android platform development, their role is complementary to the systems languages rather than interchangeable.\nWe introduced Rust into Android\nas a direct alternative to C and C++, offering a similar level of control but without many of their risks. We focus this analysis on new and actively developed code because our data shows this to be\nan effective approach\n.\n\nWhen we look at development in systems languages (excluding Java and Kotlin), two trends emerge: a steep rise in Rust usage and a slower but steady decline in new C++.\n\nNet lines of code added: Rust vs. C++, first-party Android code.\nThis chart focuses on first-party (Google-developed) code (unlike the previous chart that included all first-party and third-party code in Android.) We only include systems languages, C/C++ (which is primarily C++), and Rust.\n\nThe chart shows that the volume of new Rust code now rivals that of C++, enabling reliable comparisons of software development process metrics. To measure this, we use the DORA\n1\nframework, a decade-long research program that has become the industry standard for evaluating software engineering team performance.\nDORA metrics\nfocus on:\n\nThroughput: the velocity of delivering software changes.\n\nStability: the quality of those changes.\n\nCross-language comparisons can be challenging. We use several techniques to ensure the comparisons are reliable.\n\nSimilar sized changes: Rust and C++ have similar functionality density, though Rust is slightly denser. This difference favors C++, but the comparison is still valid. We use\nGerrit’s change size definitions\n.\n\nSimilar developer pools: We only consider first-party changes from Android platform developers. Most are software engineers at Google, and there is considerable overlap between pools with many contributing in both.\n\nTrack trends over time: As Rust adoption increases, are metrics changing steadily, accelerating the pace, or reverting to the mean?\n\nThroughput\n\nCode review is a time-consuming and high-latency part of the development process. Reworking co…","url":"http://security.googleblog.com/2025/11/rust-in-android-move-fast-fix-things.html","published_at":"2025-11-13T16:59:00Z","updated_at":"2025-11-13T17:02:24Z","fetched_at":"2026-11-21T19:15:07.449286Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/613","html":"https://vulnwatch.ve1ve2.com/item/613"}},{"id":614,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"How Android provides the most effective protection to keep you safe from mobile scams","summary":"Posted by Lyubov Farafonova, Product Manager, Phone by Google; Alberto Pastor Nieto, Sr. Product Manager Google Messages and RCS Spam and Abuse; Vijay Pareek, Manager, Android Messaging Trust and Safety\n\nAs Cybersecurity Awareness Month wraps up, we’re focusing on one of today's most pervasive digital threats: mobile scams. In the last 12 months, fraudsters have used advanced AI tools to create more convincing schemes, resulting in over $400 billion in stolen funds globally.\n¹\n\nFor years, Android has been on the frontlines in the battle against scammers, using the best of Google AI to build proactive, multi-layered protections that can anticipate and block scams before they reach you. Android’s scam defenses protect users around the world from over 10 billion suspected malicious calls and messages every month\n2\n. In addition, Google continuously performs safety checks to maintain the integrity of the RCS service. In the past month alone, this ongoing process blocked over 100 million suspicious numbers from using RCS, stopping potential scams before they could even be sent.\n\nTo show how our scam protections work in the real world, we asked users and independent security experts to compare how well Android and iOS protect you from these threats. We're also releasing a new\nreport\nthat explains how modern text scams are orchestrated, helping you understand the tactics fraudsters use and how to spot them.\n\nSurvey shows Android users’ confidence in scam protections\n\nGoogle and YouGov\n3\nsurveyed 5,000 smartphone users across the U.S., India, and Brazil about their scam experiences. The findings were clear: Android users reported receiving fewer scam texts and felt more confident that their device was keeping them safe.\n\nAndroid users were 58% more likely than iOS users to say they had not received any scam texts in the week prior to the survey. The advantage was even stronger on Pixel, where users were 96% more likely than iPhone owners to report zero scam texts\n4\n.\n\nAt the other end of the spectrum, iOS users were 65% more likely than Android users to report receiving three or more scam texts in a week. The difference became even more pronounced when comparing iPhone to Pixel, with iPhone users 136% more likely to say they had received a heavy volume of scam messages\n4\n.\n\nAndroid users were 20% more likely than iOS users to describe their device’s scam protections as “very effective” or “extremely effective.” When comparing Pixel to iPhone, iPhone users were 150% more likely to say their device was not effective at all in stopping mobile fraud.\n\nYouGov study findings on users’ experience with scams on Android and iOS\n\nSecurity researchers and analysts highlight Android’s AI-driven safeguards against sophisticated scams\n\nIn a recent\nevaluation\nby Counterpoint Research\n5\n, a global technology market research firm, Android smartphones were found to have the most AI-powered protections. The independent study compared the latest Pixel, Samsung, Motorola, and iPhone devices, and found that Android provides comprehensive AI-driven safeguards across ten key protection areas, including email protections, browsing protections, and on-device behavioral protections. By contrast, iOS offered AI-powered protections in only two categories. You can see the full comparison in the visual below.\n\nCounterpoint Research comparison of Android and iOS AI-powered protections\n\nCybersecurity firm Leviathan Security Group conducted a funded\nevaluation\n6\nof scam and fraud protection on the iPhone 17, Moto Razr+ 2025, Pixel 10 Pro, and Samsung Galaxy Z Fold 7. Their analysis found that Android smartphones, led by the Pixel 10 Pro, provide the highest level of default scam and fraud protection.The report particularly noted Android's robust call screening, scam detection, and real-time scam warning authentication capabilities as key differentiators. Taken together, these independent expert assessments conclude that Android’s AI-driven safeguards provide more com…","url":"http://security.googleblog.com/2025/10/how-android-protects-you-from-scams.html","published_at":"2025-10-30T16:59:00Z","updated_at":"2025-11-25T21:40:03Z","fetched_at":"2026-11-21T19:15:07.449286Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/614","html":"https://vulnwatch.ve1ve2.com/item/614"}},{"id":615,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"HTTPS by default","summary":"One year from now, with the release of Chrome 154 in October 2026, we will change the default settings of Chrome to enable “Always Use Secure Connections”. This means Chrome will ask for the user's permission before the first access to any public site without HTTPS.\n\nThe “Always Use Secure Connections” setting warns users before accessing a site without HTTPS\n\nChrome Security's mission\nis to make it safe to click on links. Part of being safe means ensuring that when a user types a URL or clicks on a link, the browser ends up where the user intended. When links don't use HTTPS, an attacker can hijack the navigation and force Chrome users to load arbitrary, attacker-controlled resources, and expose the user to malware, targeted exploitation, or social engineering attacks. Attacks like this are not hypothetical—software to hijack navigations is readily available and attackers have previously used insecure HTTP to\ncompromise user devices\nin a targeted attack.\n\nSince attackers only need a single insecure navigation, they don't need to worry that many sites have adopted HTTPS—any single HTTP navigation may offer a foothold. What's worse, many plaintext HTTP connections today are entirely invisible to users, as HTTP sites may immediately redirect to HTTPS sites. That gives users no opportunity to see Chrome's \"Not Secure\" URL bar warnings after the risk has occurred, and no opportunity to keep themselves safe in the first place.\n\nTo address this risk, we\nlaunched the “Always Use Secure Connections” setting\nin 2022 as an opt-in option. In this mode, Chrome attempts every connection over HTTPS, and shows a bypassable warning to the user if HTTPS is unavailable. We also previously discussed our intent to move\ntowards HTTPS by default\n. We now think the time has come to enable “Always Use Secure Connections” for all users by default.\n\nNow is the time.\n\nFor more than a decade, Google has published the\nHTTPS transparency report\n, which tracks the percentage of navigations in Chrome that use HTTPS. For the first several years of the report, numbers saw an impressive climb, starting at around 30-45% in 2015, and ending up around the 95-99% range around 2020. Since then, progress has largely plateaued.\n\nHTTPS adoption expressed as a percentage of main frame page loads\n\nThis rise represents a tremendous improvement to the security of the web, and demonstrates that HTTPS is now mature and widespread. This level of adoption is what makes it possible to consider stronger mitigations against the remaining insecure HTTP.\n\nBalancing user safety with friction\n\nWhile it may at first seem that 95% HTTPS means that the problem is mostly solved, the truth is that a few percentage points of HTTP navigations is still\na lot\nof navigations. Since HTTP navigations remain a regular occurrence for most Chrome users, a naive approach to warning on all HTTP navigations would be quite disruptive. At the same time, as the plateau demonstrates, doing nothing would allow this risk to persist indefinitely. To balance these risks, we have taken steps to ensure that we can help the web move towards safer defaults, while limiting the potential annoyance warnings will cause to users.\n\nOne way we're balancing risks to users is by making sure Chrome does not warn about the same sites excessively. In all variants of the \"Always Use Secure Connections\" settings, so long as the user regularly visits an insecure site, Chrome will not warn the user about that site repeatedly. This means that rather than warn users about 1 out of 50 navigations, Chrome will only warn users when they visit a new (or not recently visited) site without using HTTPS.\n\nTo further address the issue, it's important to understand what sort of traffic is still using HTTP. The largest contributor to insecure HTTP by far, and the largest contributor to variation across platforms, is insecure navigations to\nprivate\nsites. The graph above includes both those to public sites, such as\nexample.com\n, and navigati…","url":"http://security.googleblog.com/2025/10/https-by-default.html","published_at":"2025-10-28T17:01:00Z","updated_at":"2025-10-28T21:16:37Z","fetched_at":"2026-11-21T19:15:07.449287Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/615","html":"https://vulnwatch.ve1ve2.com/item/615"}},{"id":616,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Accelerating adoption of AI for cybersecurity at DEF CON 33","summary":"Posted by Elie Bursztein and Marianna Tishchenko, Google Privacy, Safety and Security Team\nEmpowering cyber defenders with AI is critical to tilting the cybersecurity balance back in their favor as they battle cybercriminals and keep users safe. To help accelerate adoption of AI for cybersecurity workflows, we partnered with Airbus at DEF CON 33 to host the\nGenSec Capture the Flag (CTF)\n, dedicated to human-AI collaboration in cybersecurity. Our goal was to create a fun, interactive environment, where participants across various skill levels could explore how AI can accelerate their daily cybersecurity workflows.\nAt GenSec CTF, nearly 500 participants successfully completed introductory challenges, with 23% of participants using AI for cybersecurity for the very first time. An overwhelming 85% of all participants found the event useful for learning how AI can be applied to security workflows. This positive feedback highlights that AI-centric CTFs can play a vital role in speeding up AI education and adoption in the security community.\nThe CTF also offered a valuable opportunity for the community to use\nSec-Gemini\n, Google’s experimental Cybersecurity AI, as an optional assistant available in the UI alongside major LLMs. And we received great feedback on Sec-Gemini, with 77% of respondents saying that they had found Sec-Gemini either “very helpful” or “extremely helpful” in assisting them with solving the challenges.\nWe want to thank the DEF CON community for the enthusiastic participation and for making this inaugural event a resounding success. The community feedback during the event has been invaluable for understanding how to improve Sec-Gemini, and we are already incorporating some of the lessons learned into the next iteration.\nWe are committed to advancing the AI cybersecurity frontier and will continue working with the community to build tools that help protect people online. Stay tuned as we plan to share more research and key learnings from the CTF with the broader community.","url":"http://security.googleblog.com/2025/09/accelerating-adoption-of-ai-for.html","published_at":"2025-09-24T18:42:00Z","updated_at":"2025-09-24T19:07:00Z","fetched_at":"2026-11-21T19:15:07.449288Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/616","html":"https://vulnwatch.ve1ve2.com/item/616"}},{"id":617,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Supporting Rowhammer research to protect the DRAM ecosystem","summary":"Posted by Daniel Moghimi\nRowhammer is a complex class of vulnerabilities across the industry. It is a hardware vulnerability in DRAM where repeatedly accessing a row of memory can cause bit flips in adjacent rows, leading to data corruption. This can be exploited by attackers to gain unauthorized access to data, escalate privileges, or cause denial of service. Hardware vendors have deployed various mitigations, such as\nECC\nand Target Row Refresh (TRR) for DDR5 memory, to mitigate Rowhammer and enhance DRAM reliability. However, the resilience of those mitigations against sophisticated attackers remains an open question.\nTo address this gap and help the ecosystem with deploying robust defenses, Google has supported academic research and developed test platforms to analyze DDR5 memory. Our effort has led to the discovery of new attacks and a deeper understanding of Rowhammer on the current DRAM modules, helping to forge the way for further, stronger mitigations.\nWhat is Rowhammer?\nRowhammer\nexploits a vulnerability in DRAM. DRAM cells store data as electrical charges, but these electric charges leak over time, causing data corruption. To prevent data loss, the memory controller periodically refreshes the cells. However, if a cell discharges before the refresh cycle, its stored bit may corrupt. Initially considered a reliability issue, it has been leveraged by security researchers to demonstrate privilege escalation attacks. By repeatedly accessing a memory row, an attacker can cause bit flips in neighboring rows. An adversary can exploit Rowhammer via:\nReliably cause bit flips\nby repeatedly accessing adjacent DRAM rows.\nCoerce other applications\nor the OS into using these vulnerable memory pages.\nTarget security-sensitive code or data\nto achieve privilege escalation.\nOr simply corrupt system’s memory to\ncause denial of service\n.\nPrevious work has repeatedly demonstrated the possibility of such attacks from software [\nRevisiting rowhammer\n,\nAre we susceptible to rowhammer?\n,\nDrammer\n,\nFlip feng shui\n,\nJolt\n]. As a result, defending against Rowhammer is required for secure isolation in multi-tenant environments like the cloud.\nRowhammer Mitigations\nThe primary approach to mitigate Rowhammer is to detect which memory rows are being aggressively accessed and refreshing nearby rows before a bit flip occurs. TRR is a common example, which uses a number of counters to track accesses to a small number of rows adjacent to a potential victim row. If the access count for these aggressor rows reaches a certain threshold, the system issues a refresh to the victim row. TRR can be incorporated within the DRAM or in the host CPU.\nHowever, this mitigation is not foolproof. For example, the\nTRRespass\nattack showed that by simultaneously hammering multiple, non-adjacent rows, TRR can be bypassed. Over the past couple of years, more sophisticated attacks [\nHalf-Double\n,\nBlacksmith\n] have emerged, introducing more efficient attack patterns.\nIn response, one of our efforts was to collaborate with\nJEDEC\n, external researchers, and experts to define the\n\nPRAC\nas a new mitigation that deterministically detects Rowhammer by tracking all memory rows.\nHowever, current systems equipped with DDR5 lack support for PRAC or other robust mitigations. As a result, they rely on probabilistic approaches such as ECC and enhanced TRR\n\nto reduce the risk. While these measures have mitigated older attacks, their overall effectiveness against new techniques was not fully understood until our recent\nfindings\n.\nChallenges with Rowhammer Assessment\nMitigating Rowhammer attacks involves making it difficult for an attacker to reliably cause bit flips from software. Therefore, for an effective mitigation, we have to understand how a determined adversary introduces memory accesses that bypass existing mitigations. Three key information components can help with such an analysis:\nHow the improved TRR and in-DRAM ECC work.\nHow memory access patterns from software translate into…","url":"http://security.googleblog.com/2025/09/supporting-rowhammer-research-to.html","published_at":"2025-09-15T17:01:00Z","updated_at":"2025-09-15T17:01:03Z","fetched_at":"2026-11-21T19:15:07.449288Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":null,"product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/617","html":"https://vulnwatch.ve1ve2.com/item/617"}},{"id":618,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"How Pixel and Android are bringing a new level of trust to your images with C2PA Content Credentials","summary":"Posted by Eric Lynch, Senior Product Manager, Android Security, and Sherif Hanna, Group Product Manager, Google C2PA Core\n\nAt Made by Google 2025, we announced that the new Google Pixel 10 phones will support C2PA\nContent Credentials\nin\nPixel Camera\nand\nGoogle Photos\n. This announcement represents a series of steps towards greater digital media transparency:\n\nThe Pixel 10 lineup is the first to have Content Credentials built in\n\nacross every photo created by Pixel Camera.\n\nThe Pixel Camera app\nachieved Assurance Level 2\n, the highest security rating\ncurrently defined\nby the C2PA Conformance Program. Assurance Level 2 for a mobile app is currently\nonly possible on the Android platform\n.\n\nA private-by-design\napproach to C2PA certificate management, where no image or group of images can be related to one another or the person who created them.\n\nPixel 10 phones support\non-device trusted time-stamps,\nwhich ensures images captured with your native camera app can be trusted after the certificate expires, even if they were captured when your device was offline.\n\nThese capabilities are\npowered by Google Tensor G5\n, Titan M2 security chip, the advanced hardware-backed security features of the Android platform, and Pixel engineering expertise.\n\nIn this post, we’ll break down our architectural blueprint for bringing a new level of trust to digital media, and how developers can apply this model to their own apps on Android.\n\nA New Approach to Content Credentials\n\nGenerative AI can help us all to be more creative, productive, and innovative. But it can be hard to tell the difference between content that’s been AI-generated, and content created without AI. The ability to verify the source and history—or provenance—of digital content is more important than ever.\n\nContent Credentials convey a rich set of information about how media such as images, videos, or audio files were made, protected by the same digital signature technology that has secured online transactions and mobile apps for decades. It empowers users to identify AI-generated (or altered) content, helping to foster transparency and trust in generative AI. It can be complemented by watermarking technologies such as\nSynthID\n.\n\nContent Credentials are an\nindustry standard backed by a broad coalition of leading companies\nfor securely conveying the origin and history of media files. The standard is developed by the Coalition for Content Provenance and Authenticity (C2PA), of which Google is a steering committee member.\n\nThe traditional approach to classifying digital image content has focused on categorizing content as “AI” vs. “not AI”. This has been the basis for many\nlegislative efforts\n, which have required the labeling of synthetic media. This traditional approach has drawbacks, as described in Chapter 5 of\nthis seminal report\nby Google. Research shows that if only synthetic content is labeled as “AI”, then users falsely believe unlabeled content is “not AI”, a phenomenon called “the implied truth effect”. This is why Google is taking a different approach to applying C2PA Content Credentials.\n\nInstead of categorizing digital content into a simplistic “AI” vs. “not AI”, Pixel 10 takes the first steps toward implementing our vision of categorizing digital content as either i) media that comes with verifiable proof of how it was made or ii) media that doesn't.\n\nPixel Camera\nattaches Content Credentials to any JPEG photo capture, with the appropriate description as defined by the Content Credentials specification for each capture mode.\n\nGoogle Photos\nattaches Content Credentials to JPEG images that already have Content Credentials and are edited using AI or non-AI tools, and also to any images that are edited using AI tools. It will validate and display Content Credentials under a new section in the About panel, if the JPEG image being viewed contains this data. Learn more about it in\nGoogle Photos Help\n.\n\nGiven the broad range of scenarios in which Content Credentials are attached by…","url":"http://security.googleblog.com/2025/09/pixel-android-trusted-images-c2pa-content-credentials.html","published_at":"2025-09-10T15:59:00Z","updated_at":"2025-09-10T15:59:36Z","fetched_at":"2026-11-21T19:15:07.449289Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android security","pixel"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/618","html":"https://vulnwatch.ve1ve2.com/item/618"}},{"id":619,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Android’s pKVM Becomes First Globally Certified Software to Achieve Prestigious SESIP Level 5 Security Certification","summary":"Posted by Dave Kleidermacher, VP Engineering, Android Security & Privacy\n\nToday marks a watershed moment and new benchmark for open-source security and the future of consumer electronics. Google is proud to announce that protected KVM (pKVM), the hypervisor that powers the Android Virtualization Framework, has officially achieved\nSESIP Level 5 certification\n. This makes pKVM the first software security system designed for large-scale deployment in consumer electronics to meet this assurance bar.\nSupporting Next-Gen Android Features\n\nThe implications for the future of secure mobile technology are profound. With this level of security assurance, Android is now positioned to securely support the next generation of high-criticality isolated workloads. This includes vital features, such as on-device AI workloads that can operate on ultra-personalized data, with the highest assurances of privacy and integrity.\n\nThis certification required a hands-on evaluation by\nDekra\n, a globally recognized cybersecurity certification lab, which conducted an evaluation against the\nTrustCB SESIP scheme\n, compliant to\nEN-17927\n. Achieving Security Evaluation Standard for IoT Platforms (SESIP) Level 5 is a landmark because it incorporates AVA_VAN.5, the highest level of vulnerability analysis and penetration testing under the ISO 15408 (Common Criteria) standard. A system certified to this level has been evaluated to be resistant to highly skilled, knowledgeable, well-motivated, and well-funded attackers who may have insider knowledge and access.\n\nThis certification is the cornerstone of the next-generation of Android’s multi-layered security strategy. Many of the TEEs (Trusted Execution Environments) used in the industry have not been formally certified or have only achieved lower levels of security assurance. This inconsistency creates a challenge for developers looking to build highly critical applications that require a robust and verifiable level of security. The certified pKVM changes this paradigm entirely. It provides a single, open-source, and exceptionally high-quality firmware base that all device manufacturers can build upon.\n\nLooking ahead, Android device manufacturers will be required to use isolation technology that meets this same level of security for various security operations that the device relies on. Protected KVM ensures that every user can benefit from a consistent, transparent, and verifiably secure foundation.\n\nA Collaborative Effort\n\nThis achievement represents just one important aspect of the immense, multi-year dedication from the Linux and KVM developer communities and multiple engineering teams at Google developing pKVM and\nAVF\n. We look forward to seeing the open-source community and Android ecosystem continue to build on this foundation, delivering a new era of high-assurance mobile technology for users.","url":"http://security.googleblog.com/2025/08/Android-pKVM-Certified-SESIP-Level-5.html","published_at":"2025-08-12T16:00:00Z","updated_at":"2025-10-06T01:12:36Z","fetched_at":"2026-11-21T19:15:07.449290Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["android","android security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/619","html":"https://vulnwatch.ve1ve2.com/item/619"}},{"id":620,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Introducing OSS Rebuild: Open Source, Rebuilt to Last","summary":"Posted by Matthew Suozzo, Google Open Source Security Team (GOSST)\nToday we're excited to announce OSS Rebuild, a new project to strengthen trust in open source package ecosystems by reproducing upstream artifacts. As supply chain attacks continue to target widely-used dependencies, OSS Rebuild gives security teams powerful data to avoid compromise without burden on upstream maintainers.\nThe project comprises:\nAutomation\nto derive declarative build definitions for existing PyPI (Python), npm (JS/TS), and Crates.io (Rust) packages.\nSLSA Provenance\nfor thousands of packages across our supported ecosystems, meeting SLSA Build Level 3 requirements with no publisher intervention.\nBuild observability and verification tools\nthat security teams can integrate into their existing vulnerability management workflows.\nInfrastructure definitions\nto allow organizations to easily run their own instances of OSS Rebuild to rebuild, generate, sign, and distribute provenance.\nChallenges\nOpen source software has become the foundation of our digital world. From critical infrastructure to everyday applications, OSS components now account for\n77%\nof modern applications. With an estimated value exceeding\n$12 trillion\n, open source software has never been more integral to the global economy.\nYet this very ubiquity makes open source an attractive target: Recent high-profile supply chain attacks have demonstrated sophisticated methods for compromising widely-used packages. Each incident erodes trust in open ecosystems, creating hesitation among both contributors and consumers.\nThe security community has responded with initiatives like\nOpenSSF Scorecard\n,\npypi's Trusted Publishers\n, and\nnpm's native SLSA support\n. However, there is no panacea: Each effort targets a certain aspect of the problem, often making tradeoffs like shifting work onto publishers and maintainers.\nOur Aim\nOur aim with OSS Rebuild is to empower the security community to deeply understand and control their supply chains by making package consumption as transparent as using a source repository. Our rebuild platform unlocks this transparency by utilizing a declarative build process, build instrumentation, and network monitoring capabilities which, within the\nSLSA Build\nframework, produces fine-grained, durable, trustworthy security metadata.\nBuilding on the hosted infrastructure model that we pioneered with\nOSS Fuzz\nfor memory issue detection, OSS Rebuild similarly seeks to use hosted resources to address security challenges in open source, this time aimed at securing the software supply chain.\nOur vision extends beyond any single ecosystem: We are committed to bringing supply chain transparency and security to all open source software development. Our initial support for the PyPI (Python), npm (JS/TS), and Crates.io (Rust) package registries—providing rebuild provenance for many of their most popular packages—is just the beginning of our journey.\nHow OSS Rebuild Works\nThrough automation and heuristics, we determine a prospective build definition for a target package and rebuild it. We semantically compare the result with the existing upstream artifact, normalizing each one to remove instabilities that cause bit-for-bit comparisons to fail (e.g. archive compression). Once we reproduce the package, we publish the build definition and outcome via\nSLSA Provenance\n. This attestation allows consumers to reliably verify a package's origin within the source history, understand and repeat its build process, and customize the build from a known-functional baseline (or maybe even use it to generate more detailed\nSBOMs\n).\nWith OSS Rebuild's existing automation for PyPI, npm, and Crates.io, most packages obtain protection effortlessly without user or maintainer intervention. Where automation isn't currently able to fully reproduce the package, we offer manual build specification so the whole community benefits from individual contributions.\nAnd we are also excited at the potential for AI to help re…","url":"http://security.googleblog.com/2025/07/introducing-oss-rebuild-open-source.html","published_at":"2025-07-21T21:34:00Z","updated_at":"2025-08-04T21:40:56Z","fetched_at":"2026-11-21T19:15:07.449290Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/620","html":"https://vulnwatch.ve1ve2.com/item/620"}},{"id":621,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Advancing Protection in Chrome on Android","summary":"Posted by David Adrian, Javier Castro & Peter Kotwicz, Chrome Security Team\n\nAndroid recently announced\nAdvanced Protection\n, which extends Google’s\nAdvanced Protection Program\nto a device-level security setting for Android users that need heightened security—such as journalists, elected officials, and public figures. Advanced Protection gives you the ability to activate Google’s strongest security for mobile devices, providing greater peace of mind that you’re better protected against the most sophisticated threats.\n\nAdvanced Protection acts as a single control point for at-risk users on Android that enables important security settings across applications, including many of your favorite Google apps, including Chrome. In this post, we’d like to do a deep dive into the Chrome features that are integrated with Advanced Protection, and how enterprises and users outside of Advanced Protection can leverage them.\n\nAndroid Advanced Protection integrates with Chrome on Android in three main ways:\n\nEnables the “Always Use Secure Connections”\nsetting for both public and private sites, so that users are protected from attackers reading confidential data or injecting malicious content into insecure plaintext HTTP connections. Insecure HTTP represents less than 1% of page loads for Chrome on Android.\n\nEnables full Site Isolation\non mobile devices\n\nwith 4GB+ RAM, so that potentially malicious sites are never loaded in the same process as legitimate websites. Desktop Chrome clients already have full Site Isolation.\n\nReduces attack surface\nby disabling Javascript optimizations, so that Chrome has a smaller attack surface and is harder to exploit.\n\nLet’s take a look at all three, learn what they do, and how they can be controlled outside of Advanced Protection.\n\nAlways Use Secure Connections\n\n“Always Use Secure Connections” (also known as HTTPS-First Mode in blog posts and HTTPS-Only Mode in the enterprise policy) is a Chrome setting that forces HTTPS wherever possible, and asks for explicit permission from you before connecting to a site insecurely. There may be attackers attempting to interpose on connections on any network, whether that network is a coffee shop, airport, or an Internet backbone. This setting protects users from these attackers reading confidential data and injecting malicious content into otherwise innocuous webpages. This is particularly useful for Advanced Protection users, since in 2023, plaintext HTTP was\nused as an exploitation vector during the Egyptian election\n.\n\nBeyond Advanced Protection, we\npreviously posted\nabout how our goal is to eventually enable “Always Use Secure Connections” by default for all Chrome users. As we work towards this goal, in the last two years we have quietly been enabling it in more places beyond Advanced Protection, to help protect more users in risky situations, while limiting the number of warnings users might click through:\n\nWe added a new variant of the setting that only warns on public sites, and doesn’t warn on local networks or single-label hostnames (e.g.\n192.168.0.1\n,\nshortlink/\n,\n10.0.0.1\n). These names often cannot be issued a publicly-trusted HTTPS certificate. This variant protects against most threats—accessing a public website insecurely—but still allows for users to access local sites, which may be on a more trusted network, without seeing a warning.\n\nWe’ve automatically enabled “Always Use Secure Connections” for public sites in Incognito Mode for the last year, since Chrome 127 in June 2024.\n\nWe automatically prevent downgrades from HTTPS to plaintext HTTP on sites that Chrome knows you typically access over HTTPS (a heuristic version of the\nHSTS header\n), since Chrome 133 in January 2025.\nAlways Use Secure Connections has two modes—warn on insecure public sites, and warn on any insecure site.\n\nAny user can enable “Always Use Secure Connections” in the Chrome Privacy and Security settings, regardless of if they’re using Advanced Protection. Users can choose if they woul…","url":"http://security.googleblog.com/2025/07/advancing-protection-in-chrome-on.html","published_at":"2025-07-08T17:36:00Z","updated_at":"2025-07-08T17:36:01Z","fetched_at":"2026-11-21T19:15:07.449291Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":[],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/621","html":"https://vulnwatch.ve1ve2.com/item/621"}},{"id":622,"source":{"id":"google-security-blog","name":"Google Online Security Blog"},"title":"Mitigating prompt injection attacks with a layered defense strategy","summary":"Posted by Adam Gavish, Google GenAI Security Team\nWith the rapid adoption of generative AI, a new wave of threats is emerging across the industry with the aim of manipulating the AI systems themselves. One such emerging attack vector is indirect prompt injections. Unlike direct prompt injections, where an attacker directly inputs malicious commands into a prompt, indirect prompt injections involve hidden malicious instructions within external data sources. These may include emails, documents, or calendar invites that instruct AI to exfiltrate user data or execute other rogue actions. As more governments, businesses, and individuals adopt generative AI to get more done, this subtle yet potentially potent attack becomes increasingly pertinent across the industry, demanding immediate attention and robust security measures.\nAt Google, our teams have a longstanding precedent of investing in a defense-in-depth strategy, including robust evaluation, threat analysis,\nAI security best practices\n,\nAI red-teaming\n, adversarial training, and model hardening for generative AI tools. This approach enables safer adoption of\nGemini in Google Workspace\nand the\nGemini app\n(we refer to both in this blog as “Gemini” for simplicity). Below we describe our prompt injection mitigation product strategy based on extensive research, development, and deployment of improved security mitigations.\nA layered security approach\nGoogle has taken a layered security approach introducing security measures designed for each stage of the prompt lifecycle. From Gemini 2.5 model hardening, to purpose-built machine learning (ML) models detecting malicious instructions, to system-level safeguards, we are meaningfully elevating the difficulty, expense, and complexity faced by an attacker. This approach compels adversaries to resort to methods that are either more easily identified or demand greater resources.\nOur model training with adversarial data significantly enhanced our defenses against indirect prompt injection attacks in Gemini 2.5 models (\ntechnical details\n). This inherent model resilience is augmented with additional defenses that we built directly into Gemini, including:\nPrompt injection content classifiers\nSecurity thought reinforcement\nMarkdown sanitization and suspicious URL redaction\nUser confirmation framework\nEnd-user security mitigation notifications\nThis layered approach to our security strategy strengthens the overall security framework for Gemini – throughout the prompt lifecycle and across diverse attack techniques.\n1. Prompt injection content classifiers\nThrough collaboration with leading AI security researchers via\nGoogle's AI Vulnerability Reward Program (VRP)\n, we've curated one of the world’s most advanced catalogs of generative AI vulnerabilities and adversarial data. Utilizing this resource, we built and are in the process of rolling out proprietary machine learning models that can detect malicious prompts and instructions within various formats, such as emails and files, drawing from real-world examples. Consequently, when users query Workspace data with Gemini, the content classifiers filter out harmful data containing malicious instructions, helping to ensure a secure end-to-end user experience by retaining only safe content. For example, if a user receives an email in Gmail that includes malicious instructions, our content classifiers help to detect and disregard malicious instructions, then generate a safe response for the user. This is in addition to built-in defenses in Gmail that automatically block more than 99.9% of spam, phishing attempts, and malware.\nA diagram of Gemini’s actions based on the detection of the malicious instructions by content classifiers.\n2. Security thought reinforcement\nThis technique adds targeted security instructions surrounding the prompt content to remind the large language model (LLM) to perform the user-directed task and ignore any adversarial instructions that could be present in the content. With th…","url":"http://security.googleblog.com/2025/06/mitigating-prompt-injection-attacks.html","published_at":"2025-06-13T16:03:00Z","updated_at":"2026-04-02T19:45:04Z","fetched_at":"2026-11-21T19:15:07.449292Z","severity":"unknown","cvss_score":null,"epss":null,"is_kev":false,"has_exploit":false,"kev_due_date":null,"vendor":"google","product":null,"vuln_id":null,"vuln_ids":[],"tags":["AI Security"],"cluster_id":null,"links":{"self":"https://vulnwatch.ve1ve2.com/api/v1/items/622","html":"https://vulnwatch.ve1ve2.com/item/622"}}],"total":25,"has_more":false,"next_cursor":null,"limit":50,"page":1,"grouped":false,"filter":{"builds":"exclude","source":"google-security-blog"}}