Finding and Fixing Vulnerabilities Using AI

9 Bibliography

• [0xkato2024] 0xkato, 2024-12-01, Get ready for an audit, https://www.0xkato.xyz/Get-ready-for-an-audit/
• [0xkato2026] 0xkato, 2026-06-01, “How LLMs Actually Work”, https://www.0xkato.xyz/how-llms-actually-work/
• [Agarwal2026] Abhinav Agarwal, 2026-04-21, “Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery”, https://arxiv.org/abs/2604.19049
• [Chen2026] Bo Chen, 2026-08-10, “From Runnable to Verifiable: An Independent Reproducibility Study of LLM/Agent-Driven Vulnerability Validation Artifacts”, https://arxiv.org/abs/2608.09567
• [Agyekum2026] Benjamin Agyekum and Fabio Santos, 2026-08-13, “Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair”, 20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026), https://arxiv.org/abs/2608.13404
• [Ahmad2026] Ahmad Osman, 2026, Anthropic’s War on Opensource AI, https://x.com/TheAhmadOsman/status/2065307070044234186
• [Alibaba2026] Alibaba, open-code-review README, https://github.com/alibaba/open-code-review
• [Aniszczyk2026] Aniszczyk, Chris (CNCF), David A. Wheeler (OpenSSF), Christopher “CRob” Robinson (OpenSSF), 2026-05, “Securing Open Source in the Age of AI”, https://openssf.org/resources/securing-open-source-in-the-age-of-ai-a-practical-guide/
• [Anthropic2026-04g] Anthropic, 2026-04, “Project Glasswing: Securing critical software for the AI era”, https://www.anthropic.com/glasswing
• [Anthropic2026-03] Anthropic, 2026-03-06, “Partnering with Mozilla to improve Firefox’s security”, https://www.anthropic.com/news/mozilla-firefox-security
• [Anthropic2026-04s] Anthropic, 2026-04-07 (actually 2026-04-08), “System Card: Claude Mythos Preview”, https://www-cdn.anthropic.com/08ab9158070959f88f296514c21b7facce6f52bc.pdf
• [Anthropic2026-06-12-Export-Control] Anthropic, 2026-06-12, Statement on the US government directive to suspend access to Fable 5 and Mythos 5, https://www.anthropic.com/news/fable-mythos-access
• [Anthropic2026-05] Anthropic, “Project Glasswing: An initial update”, 2026-05-22, https://www.anthropic.com/research/glasswing-initial-update
• [Anthropic-07-27] Anthropic, 2026-07-27, Our position on open-weights models, https://www.anthropic.com/news/position-open-weights-models
• [Anthropic2026-08-21] Anthropic, 2026-08-21, Bringing the cybersecurity capabilities of Claude Mythos 5 to more defenders, https://claude.com/blog/bringing-claude-mythos-5-to-more-defenders
• [Berkeley] Berkeley Vulnerability Initiative, https://vuln.cs.berkeley.edu/
• [Bishop2026] Bishop, Todd, 2026-05-13, “Microsoft’s multi-agent AI system tops Anthropic’s Mythos on cybersecurity benchmark”, https://www.geekwire.com/2026/microsofts-multi-agent-ai-system-tops-anthropics-mythos-on-cybersecurity-benchmark/
• [Bourzikas2026] Bourzikas, Grant, 2026-05-18, “Project Glasswing: what Mythos showed us” https://blog.cloudflare.com/cyber-frontier-models/
• [Bressers2025] Bressers, Josh, and Joshua Rogers, 2025-10-13, “Actually finding vulnerabilities using AI with Joshua Rogers”, Open Source Security Podcast, https://opensourcesecurity.io/2025/2025-10-ai-joshua-rogers/
• [Brown2026] Jarom Brown, 2026-05-15, “Raising the bar: Quality, shared responsibility, and the future of GitHub’s bug bounty program”, The GitHub Blog, https://github.blog/security/raising-the-bar-quality-shared-responsibility-and-the-future-of-githubs-bug-bounty-program/
• [Buttell2026] Amy Buttell, 2026-04-04, AI Code Risks Escalate: The use of AI coding tools continues to accelerate even as trust declines and risks proliferate, https://cacm.acm.org/news/ai-code-risks-escalate/
• [Capoot2026] Ashley Capoot, 2026-06-30, “Anthropic says Trump admin has lifted export controls on Claude Fable 5 and Mythos 5”, CNBC, https://www.cnbc.com/2026/06/30/anthropic-says-trump-admin-has-lifted-export-controls-on-claude-fable-5-and-mythos-5.html
• [Carlini2026] Nicholas Carlini, Newton Cheng, Keane Lucas, Michael Moore, Milad Nasr, Vinay Prabhushankar, Winnie Xiao, et al., 2026-04-07, “Assessing Claude Mythos Preview’s cybersecurity capabilities”, https://red.anthropic.com/2026/mythos-preview/
• [Carlini2026-youtube] Nicholas Carlini, 2026, “Black-hat LLMs”, [un]prompted 2026” https://www.youtube.com/watch?v=1sd26pWhfmg&t=316s
• [Carlini2026-02] Carlini et al., 2026-02-05, “Evaluating and mitigating the growing risk of LLM-discovered 0-days”, https://red.anthropic.com/2026/zero-days/
• [Chin2026] Andrew Chin, Dongkwan Kim, Yu-Fu Fu, Fabian Fleischer, Youngjoon Kim, HyungSeok Han, Cen Zhang, Brian Junekyu Lee, Hanqing Zhao, Taesoo Kim, 2026-03-25, “OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security”, https://arxiv.org/abs/2603.08566
• [Chin2026-slides] Andrew Chin, Brian Lee, 2026, OSS-CRS Tutorial: Bug-Finding and Patching for the LLM Era (slides), Systems Software & Security Lab (Georgia Tech) / Team Atlanta, https://github.com/ossf/oss-crs/blob/main/docs/slides/svcc-2026.pptx
• [Chrome2026] Chrome Security Team, 2026-07-30, Stronger with every update: How we’re making Chrome and the web safer in the AI Era, https://blog.google/security/chrome-stronger-with-every-update/
• [Catanzaro2026] Michael Catanzaro, 2026-06-08, https://blogs.gnome.org/mcatanzaro/2026/06/08/please-do-not-ban-ai-assisted-issue-reports/
• [Chia2026] Osmond Chia and Laura Cress, 2026-07-31, Anthropic’s Claude AI escapes to hack into three organisations, BBC, https://www.bbc.com/news/articles/cz7dl7w8y7po
• [Churilov2026] Aleksandr Churilov, 2026-05-16 (revised 2026-08-09), “The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort”, https://arxiv.org/abs/2605.17062
• [CISA2026-CVD] CISA, NSA, JPCERT/CC, NCSC-NL, and NCSC-UK, 2026-07-15, “Establishing a Coordinated Vulnerability Disclosure Program to Work With Security Researchers”, https://www.cisa.gov/resources-tools/resources/establishing-coordinated-vulnerability-disclosure-program-work-security-researchers
• [CloudFlare] CloudFlare, “Can AI find vulnerabilities?”, https://www.cloudflare.com/the-net/ai-vulnerabilities/
• [CrowdStrike2026-Global] CrowdStrike, 2026, “CrowdStrike 2026: Global Threat Report: Year of the Evasive Adversary”, https://go.crowdstrike.com/2026-global-threat-report.html
• [Cooter2026] Maxwell Cooter, 2026-04-03, “Internet Bug Bounty program hits pause on payouts”, InfoWorld, https://www.infoworld.com/article/4154210/internet-bug-bounty-program-hits-pause-on-payouts.html
• [CrowdStrike2026-FiveSteps] CrowdStrike. 2026. Five Steps for Frontier AI Security Readiness. https://www.crowdstrike.com/en-us/resources/white-papers/five-steps-for-frontier-ai-security-readiness/
• [CRA-AnnexI] Cyber Resilience Act (CRA), https://eur-lex.europa.eu/eli/reg/2024/2847/oj/eng#anx_I
• [crs-bug-finding-template] crs-bug-finding-template [for OSS-CRS], https://github.com/Team-Atlanta/crs-bug-finding-template/
• [CSA2026] CSA CISO Community, SANS, [un]prompted, OWASP Gen AI Security Project and the wider community (and many contributing authors), 2026, “The “AI Vulnerability Storm”: Building a “Mythos-ready” Security Program”, https://labs.cloudsecurityalliance.org/mythos-ciso/
• [Cycode2026] Cycode Team, 6 Steps to be Mythos Ready: How to Prepare for the AI Vulnerability Storm, 2026-05-20, https://cycode.com/blog/claude-mythos-security-readiness/
• [Daelman2025] Rein Daelman, 2025-12-04 (last updated 2026-03-17), “PromptPwnd: Prompt Injection Vulnerabilities in GitHub Actions Using AI Agents”, Aikido Security, https://www.aikido.dev/blog/promptpwnd-github-actions-ai-agents
• [DARPA2016] DARPA, 2016-08-05, “DARPA Celebrates Cyber Grand Challenge Winners”, https://www.darpa.mil/news/2016/cyber-grand-challenge-winners
• [Diecks2026] Diecks, Jeff, 2026-04-02, “From AIxCC to OpenSSF: Welcoming OSS-CRS to Advance AI Driven”, https://openssf.org/blog/2026/04/02/from-aixcc-to-openssf-welcoming-oss-crs-to-advance-ai-driven-open-source-security/
• [Dinaburg2026] Artem Dinaburg, 2026-08-26, VMs won’t contain cyber-capable agents, Trail of Bits, https://blog.trailofbits.com/2026/08/26/vms-wont-contain-cyber-capable-agents/
• [Ding2025] Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim, Chawin Sitawarin, Xinyun Chen, Basel Alomair, David Wagner, Baishakhi Ray, and Yizheng Chen, 2025, “Vulnerability Detection with Code Language Models: How Far Are We?”, 47th IEEE/ACM International Conference on Software Engineering (ICSE 2025), https://arxiv.org/abs/2403.18624
• [Dominus2026-03-05] Mark Dominus, 2026-03-05, Documentation is a message in a bottle, https://blog.plover.com/tech/gpt/documentation-wins.html
• [Dominus2026-03-09] Mark Dominus, 2026-03-09, “Programmers will document for Claude, but not for each other”, Blog post, https://blog.plover.com/tech/gpt/documentation-wins-2.html
• [Donnelly2026] Donnelly, Tommy, 2026-04-15, “AI Is Finding Vulnerabilities Faster Than You Can Patch Them. Now What?” https://www.amplifiersecurity.com/blog/ai-vulnerability-management-mythos
• [FiveEyes2026] Five Eyes, 2026-06-22, Five Eyes cyber security agencies statement, https://www.cyber.gov.au/sites/default/files/2026-06/Five%20eyes%20cyber%20security%20agencies%20statement.pdf
• [Gerstenhaber2026] Michael Gerstenhaber and Clemens Viernickel, 2026-07-21, “Now in preview: Find and fix software vulnerabilities with CodeMender”, Google Cloud Blog, https://cloud.google.com/blog/products/identity-security/find-and-fix-software-vulnerabilities-with-codemender
• [Google-CodeMender-Docs] Google Cloud, “CodeMender overview”, Gemini Enterprise Agent Platform documentation (accessed 2026-09-29), https://docs.cloud.google.com/gemini-enterprise-agent-platform/codemender
• [Grinstead2026-03] Grinstead, Brian, Christian Holler, 2026-03-06, “Hardening Firefox with Anthropic’s Red Team” https://blog.mozilla.org/en/firefox/hardening-firefox-anthropic-red-team/
• [Grinstead2026-05] Grinstead, Brian, Christian Holler, Frederik Braun, 2026-05-07, “Behind the Scenes Hardening Firefox with Claude Mythos Preview”, https://hacks.mozilla.org/2026/05/behind-the-scenes-hardening-firefox/
• [Guan2026] Aonan Guan, with Zhengyu Liu and Gavin Zhong, 2026-04-15, “Comment and Control: Prompt Injection to Credential Theft in Claude Code, Gemini CLI, and GitHub Copilot Agent”, https://oddguan.com/blog/comment-and-control-prompt-injection-credential-theft-claude-code-gemini-cli-github-copilot/
• [Hart2026] Robert Hart, 2026-09-25, One company is at the center of a wave of rogue AI attacks: Mistakes at Israeli startup Irregular sent Anthropic, OpenAI, Meta, and Google agents after real-world targets, https://www.theverge.com/ai-artificial-intelligence/1000644/irregular-rogue-ai-cyberattacks-hacking-openai-meta-anthropic-google
• [Harzevili2024] Nima Shiri Harzevili, Alvine Boaye Belle, Junjie Wang, Song Wang, Zhen Ming (Jack) Jiang, and Nachiappan Nagappan. 2024. “A Systematic Literature Review on Automated Software Vulnerability Detection Using Machine Learning.” ACM Comput. Surv. 57, 3, Article 55 (Nov. 2024), 36 pages. https://doi.org/10.1145/3699711
• [Hellekson2026] Gunnar Hellekson et al, 2026-04-08, “Navigating the Mythos-haunted world of platform security”, https://www.redhat.com/en/blog/navigating-mythos-haunted-world-platform-security
• [Hillah2026] Lom M. Hillah, Jean-Marc Richard, and Ryan Hasnaoui, 2026-06-11, “Bayesian-Calibrated Detection of Hallucinated Package Imports in AI-Assisted Code”, https://arxiv.org/abs/2606.13918
• [Holterhoff2026] Holterhoff, Kate, 2026-05-05, “AI Slop & the Vulnerability Treadmill”, https://redmonk.com/kholterhoff/2026/05/05/ai-slop-vulnerability-treadmill/
• [Holley2026] Bobby Holley, 2026-04-21, “The zero-days are numbered”, https://blog.mozilla.org/en/privacy-security/ai-security-zero-day-vulnerabilities/
• [Hoodlet2026] Keith Hoodlet, 2026-08-06, Vulnerability patches still require expert human review, https://1password.com/blog/why-ai-generated-patches-still-require-human-review
• [HuggingFace2026] Hugging Face, 2026-07-16, Security incident disclosure — July 2026, https://huggingface.co/blog/security-incident-july-2026
• [Karbasi2026] Amin Karbasi, Supriti Vijay, Aman Priyanshu, Didier Chapoteau, Arthur Goldblatt, Kimia Majd, Fraser Burch, Jianliang He, Baturay Saglam, Takahiro Matsumoto, Zhuoran Yang, 2026-06-21, Introducing Antares: Highly Efficient Open Weight AI Models for Vulnerability Localization, https://blogs.cisco.com/ai/introducing-antares-the-most-efficient-open-weight-ai-models-for-vulnerability-localization
• [Kholoosi2025] M. Mehdi Kholoosi, Triet Huynh Minh Le, M. Ali Babar, 2025-12-23, “Software Vulnerability Management in the Era of Artificial Intelligence: An Industry Perspective”, https://arxiv.org/abs/2512.18261v2
• [Kim2026] Kim Taesoo (VP, Agentic Security, Microsoft), 2026-05-12, “Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark”, https://www.microsoft.com/en-us/security/blog/2026/05/12/defense-at-ai-speed-microsofts-new-multi-model-agentic-security-system-tops-leading-industry-benchmark/
• [Korda2026] Nahum Korda and Gadi Evron, 2026-06-17, “OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing”, https://arxiv.org/abs/2606.19149
• [Kovacs2026-08-24] Eduard Kovacs, 2026-08-24, Anthropic Expands Mythos 5 Access to More Defenders, Unveils $35M Open Source Fund, https://www.securityweek.com/anthropic-expands-mythos-5-access-to-more-defenders-unveils-35m-open-source-fund/
• [Kurmi2025] Ashish Kurmi, 2025-08-27, “s1ngularity: Popular Nx Build System Package Compromised with Data-Stealing Malware”, StepSecurity, https://www.stepsecurity.io/blog/supply-chain-security-alert-popular-nx-build-system-package-compromised-with-data-stealing-malware
• [Kwa2025] Thomas Kwa, Ben West, Joel Becker, Amy Deng, Katharyn Garcia, Max Hasin, Sami Jawhar, Megan Kinniment, Nate Rush, Sydney Von Arx, Ryan Bloom, Thomas Broadley, Haoxing Du, Brian Goodrich, Nikola Jurkovic, Luke Harold Miles, Seraphina Nix, Tao Lin, Neev Parikh, David Rein, Lucas Jun Koba Sato, Hjalmar Wijk, Daniel M. Ziegler, Elizabeth Barnes, Lawrence Chan, 2026-02-25, “Measuring AI Ability to Complete Long Software Tasks”, https://arxiv.org/abs/2503.14499
• [Kwa2025-blog] Thomas Kwa, Ben West, Joel Becker, et al., 2025-03-19, https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/
• [Lakshmanan2026] Ravie Lakshmanan, 2026-05-12, “OpenAI Launches Daybreak for AI-Powered Vulnerability Detection and Patch Validation”, The Hacker News, https://thehackernews.com/2026/05/openai-launches-daybreak-for-ai-powered.html
• [Larson2026] Seth Larsen, 2026-02-24, Respecting maintainer time should be in security policies, https://sethmlarson.dev/respecting-maintainer-time-should-be-in-security-policies
• [Li2026] Fengjie Li, Jiajun Jiang, Dongchi Chen, and Yingfei Xiong, 2026-01-27 (revised 2026-09-25), “LLM-based Vulnerability Detection at Project Scale: An Empirical Study”, https://arxiv.org/abs/2601.19239
• [Licklider1960] J. C. R. “Lick” Licklider, 1960-03, Man-Computer Symbiosis, IRE Transactions on Human Factors in Electronics, volume HFE-1, pages 4-11, https://groups.csail.mit.edu/medg/people/psz/Licklider.html
• [Li2025] Yue Li, Xiao Li, Hao Wu, Minghui Xu, Yue Zhang, Xiuzhen Cheng, Fengyuan Xu, Sheng Zhong, 2025-04-18, Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask, https://arxiv.org/abs/2504.13474v1
• [Linux-AI] Linux kernel developers, “AI Coding Assistants”, The Linux Kernel documentation, https://docs.kernel.org/process/coding-assistants.html
• [Linux-SecurityBugs] Linux kernel developers, “Security bugs”, The Linux Kernel documentation, https://docs.kernel.org/process/security-bugs.html
• [LowLevel2026] Low Level, 2026, “Mythos has been unleashed (we have results)” [video], https://www.youtube.com/watch?v=IS4OgH74gY4
• [Microsoft2026-07] Microsoft, 2026-07-24, Open Weights and American AI Leadership, https://www.microsoft.com/en-us/corporate-responsibility/topics/open-weight/
• [Mierczuk2026] Axel Mierczuk, Spencer Michaels, and Keith Hoodlet, 2026, Frontier Models’ Vulnerability Patches are Often F.L.A.W.E.D.: Fix-Like Artifacts With Embedded Defects: Common failure modes of LLM-generated security patches, https://1password.com/files/resources/frontier-models-vulnerability-patches-flawed.pdf
• [Naik2026] Anish Naik et al., 2026-09-15, 1Password’s AI patching benchmark is misleading, Trail of Bits Blog, https://blog.trailofbits.com/2026/09/15/1passwords-ai-patching-benchmark-is-misleading/
• [Nesbitt2026-06] Andrew Nesbitt, 2026-06-25, Scrutineer: scanning open source without flooding maintainers, https://nesbitt.io/2026/06/25/scrutineer.html
• [NIST-AgentIdentity2026] NIST NCCoE, 2026-02-05, “Accelerating the Adoption of Software and Artificial Intelligence Agent Identity and Authorization”, https://www.nccoe.nist.gov/projects/software-and-ai-agent-identity-and-authorization
• [NPR2026] Huo Jingnan, 2026-04-11, How AI is getting better at finding security holes, https://www.npr.org/2026/04/11/nx-s1-5778508/anthropic-project-glasswing-ai-cybersecurity-mythos-preview
• [NVIDIA2026] NVIDIA, 2026, Industry Leaders Unite in Open Secure AI Alliance for AI Safety and Security, https://blogs.nvidia.com/blog/open-secure-ai-alliance/
• [OpenAI2026-07] OpenAI, 2026-07-21, OpenAI and Hugging Face partner to address security incident during model evaluation, https://openai.com/index/hugging-face-model-evaluation-security-incident/
• [OpenSSF2025-AIInstructions] OpenSSF Best Practices and AI/ML Working Groups (led by Avishay Balter), 2025-08-01, “Security-Focused Guide for AI Code Assistant Instructions”, https://best.openssf.org/Security-Focused-Guide-for-AI-Code-Assistant-Instructions.html
• [OpenSSF2026-06] Open Source Security Foundation (OpenSSF) Best Practices Working Group, 2026-06-30, Compiler Options Hardening Guide for C and C++, https://best.openssf.org/Compiler-Hardening-Guides/Compiler-Options-Hardening-Guide-for-C-and-C++.html
• [Oshungboye] Oshungboye, Damilola, UNK-04-22, “How to use AI to identify and fix security vulnerabilities in your codebase”, CodeRabbit, https://dev.to/coderabbitai/how-to-use-ai-to-identify-and-fix-security-vulnerabilities-in-your-codebase-4na2
• [Ottenheimer2026-05-26] David Ottenheimer, 2026-05-26, Mythos Grading Mythos: Got Patches Yet?, https://www.flyingpenguin.com/mythos-grading-mythos-got-patches-yet/
• [OWASP2025-AITesting] OWASP, 2025-11-26, OWASP AI Testing Guide, https://owasp.org/www-project-ai-testing-guide/
• [OWASP-Agentic2026] OWASP GenAI Security Project, 2025-12-09, “OWASP Top 10 for Agentic Applications for 2026”, https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/
• [OWASP-ASI06] Idan Habler, OWASP GenAI Security Project, 2026-05-13, “Memory Is a Feature. It Is Also an Attack Surface”, https://genai.owasp.org/2026/05/13/memory-is-a-feature-it-is-also-an-attack-surface/
• [OWASP-ASVS5] OWASP, 2025, “OWASP Application Security Verification Standard 5.0.0”, (especially V2.2.2 and V8.3.1), https://owasp.org/www-project-application-security-verification-standard/
• [OWASP-LLM01] OWASP GenAI Security Project, “LLM01: Prompt Injection”, https://genai.owasp.org/llmrisk/llm01-prompt-injection/
• [OWASP-LLM06] OWASP GenAI Security Project, “LLM06:2025 Excessive Agency”, https://genai.owasp.org/llmrisk/llm062025-excessive-agency
• [OWASP-ASVS5-V7] OWASP, 2025, “OWASP Application Security Verification Standard 5.0.0”, particularly V7 Session Management, https://github.com/OWASP/ASVS/blob/master/5.0/en/0x16-V7-Session-Management.md
• [OWASP-GenAI] OWASP GenAI Security Project, https://genai.owasp.org/
• [OWASP-LLM10] OWASP GenAI Security Project, “LLM10:2025 Unbounded Consumption”, https://genai.owasp.org/llmrisk/llm102025-unbounded-consumption
• [Pardesi2026-08-05] Rajveer Pardesi and Mrinmay Dey, 2026-08-05, Meta AI model hacks another company during testing, Reuters, https://www.reuters.com/technology/metas-ai-model-hacked-another-company-during-testing-information-reports-2026-08-05/
• [Perry2023] Neil Perry, Megha Srivastava, Deepak Kumar, and Dan Boneh, 2023-11, “Do Users Write More Insecure Code with AI Assistants?”, Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS ’23), https://arxiv.org/abs/2211.03622
• [PSF2026] Python Software Foundation (PSF), 2026-06-17, “Everything Security at PyCon US 2026”, https://pyfound.blogspot.com/2026/06/everything-security-at-pycon-us-2026.html
• [Reuters2026-08-07] Reuters, 2026-08-07, Chinese startup Moonshot’s AI model breaks out of testing environment, researchers say, https://www.reuters.com/legal/litigation/chinese-startup-moonshots-ai-model-breaks-out-testing-environment-researchers-2026-08-07/
• [Risse2025] Niklas Risse, Jing Liu, and Marcel Böhme, 2025, “Top Score on the Wrong Exam: On Benchmarking in Machine Learning for Vulnerability Detection”, Proceedings of the ACM on Software Engineering (ISSTA 2025), https://arxiv.org/abs/2408.12986
• [Rohlf2025] Rohlf, Chris, 2025-08-04, AI and the Software Vulnerability Lifecycle, https://cset.georgetown.edu/article/ai-and-the-software-vulnerability-lifecycle/
• [Rogers2025] Rogers, Joshua, 2025, “Hacking with AI SASTs: An overview of ‘AI Security Engineers’ / ‘LLM Security Scanners’ for Penetration Testers and Security Teams”, https://joshua.hu/llm-engineer-review-sast-security-ai-tools-pentesters
• [Safdar2025] Rijha Safdar, Danyail Mateen, Syed Taha Ali, Umer Ashfaq and Wajahat Hussain, 2025, “Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection”, https://arxiv.org/abs/2508.16625v2
• [SARIF2.1] OASIS, 2020, “Static Analysis Results Interchange Format (SARIF) Version 2.1.0”, https://docs.oasis-open.org/sarif/sarif/v2.1.0/os/sarif-v2.1.0-os.html
• [Shakevsky2026] Alon Shakevsky, Corban Villa, Ion Stoica, and Raluca Ada Popa, 2026-07-14, “Antiproof: Synthesizing Vulnerability Detectors and Proofs of Exploitability”, https://arxiv.org/abs/2607.12316
• [Shimmi2025] Shimmi, Samiha, Hamed Okhravi, Mona Rahimi, 2025-06-12, “AI-Based Software Vulnerability Detection: A Systematic Literature Review”, https://arxiv.org/abs/2506.10280
• [Shein2026] Esther Shein, 2026-06-03, Investing in Workers to Work with AI: Training encourages workers to utilize AI tools to their fullest and allays fears AI will replace them, https://cacm.acm.org/news/investing-in-workers-to-work-with-ai/
• [Shen2026-09] Chihao Shen, Jiacheng Li, Aastha Mahajan, Jeffery Siyuan Tian, Yonghwi Kwon, Yizheng Chen, 2026-09-03, PatchBench: Evaluating AI Agents for Vulnerability Patching, https://arxiv.org/abs/2609.04075
• [Shostack2014] Adam Shostack, 2014, Threat Modeling: Designing for Security.
• [Shukla2025] Shivani Shukla, Himanshu Joshi, and Romilla Syed, 2025-05-19 (revised 2025-09-26), “Security Degradation in Iterative AI Code Generation: A Systematic Analysis of the Paradox”, https://arxiv.org/abs/2506.11022
• [Silverman2024] Silverman, Micah, 2024-10-14, “Automatically fix code vulnerabilities with AI” https://snyk.io/blog/automatically-fix-code-vulnerabilities-ai/
• [Spracklen2025] Joseph Spracklen, Raveen Wijewickrama, A H M Nazmus Sakib, Anindya Maiti, Bimal Viswanath, and Murtuza Jadliwala, 2025-08, “We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs”, 34th USENIX Security Symposium (USENIX Security 25), https://www.usenix.org/conference/usenixsecurity25/presentation/spracklen
• [Steenhoek2025] Benjamin Steenhoek, Kalpathy Sivaraman, Renata Saldivar Gonzalez, Yevhen Mohylevskyy, Roshanak Zilouchian Moghaddam, Wei Le, 2025-04-25, “Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDE”, https://arxiv.org/abs/2412.14306v3
• [Stenberg2026-01] Daniel Stenberg, 2026-01-26, “The end of the curl bug-bounty”, https://daniel.haxx.se/blog/2026/01/26/the-end-of-the-curl-bug-bounty/
• [Stenberg2026-04] Daniel Stenberg, 2026-04-22, “High-Quality Chaos”, https://daniel.haxx.se/blog/2026/04/22/high-quality-chaos/
• [Stenberg2026-05a] Stenberg, Daniel, 2026-05-11, “Mythos finds a curl vulnerability”, https://daniel.haxx.se/blog/2026/05/11/mythos-finds-a-curl-vulnerability/
• [Stenberg2026-05b] Stenberg, Daniel, 2026-05, LinkedIn post, “Not even half-way through this #curl release cycle we are already at 11 confirmed vulnerabilities”, https://www.linkedin.com/posts/danielstenberg_curl-curl-share-7463481423543414786-sJew/
• [TesseractedLabs2026] Tesseracted Labs, 2026-09-15, “Enforcing coding-agent guardrails in the runtime instead of the prompt”, https://tesseracted-labs-blog.vercel.app/enforcing-coding-agent-guardrails-in-the-runtime-instead-of-the-prompt
• [TrailofBits2026-06] Trail of Bits, 2026-06-22, Introducing Patch the Planet, https://blog.trailofbits.com/2026/06/22/introducing-patch-the-planet/
• [Vaughan-Nichols2026-02] Vaughan-Nichols, Stephen J., 2026-02-15, “cURL’s Daniel Stenberg: AI slop is DDoSing open source: For open source software, AI is very much a mixed blessing in his view.” https://thenewstack.io/curls-daniel-stenberg-ai-is-ddosing-open-source-and-fixing-its-bugs/
• [Vanian2026] Jonathan Vanian, 2026-08-09, How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta, AI Age, https://www.cnbc.com/2026/08/09/israeli-startup-irregular-linked-to-ai-hacks-openai-anthropic-meta.html
• [vanZyl] van Zyl, Leon, “Claude Code: Build an AI Agent That Finds Vulnerabilities” (video), https://www.youtube.com/watch?v=VFLieg8JjLA
• [Walsh2026] Joe Walsh, 2026-08-02, CEO of AI firm Hugging Face calls last month’s hack by OpenAI model “very weird and unprecedented”, CBS News, https://www.cbsnews.com/news/hugging-face-hack-openai-rogue-model/
• [Wheeler2025] David A. Wheeler, 2025, Secure AI/ML-Driven Software Development (LFEL1012), https://training.linuxfoundation.org/express-learning/secure-ai-ml-driven-software-development-lfel1012/
• [Wheeler2026] David A. Wheeler, 2026-01-05, AI, Software Development, Security, Tips, and the Future (Part 2), OpenSSF Blog, https://openssf.org/blog/2026/01/05/ai-software-development-security-tips-and-the-future-part-2/
• [Whitehouse2026] Ollie Whitehouse (NCSC CTO), 2026-05-01, “Preparing for a ‘vulnerability patch wave’”, UK National Cyber Security Centre (NCSC), https://www.ncsc.gov.uk/blogs/prepare-for-vulnerability-patch-wave
• [Wolff2026] Dylan Wolff, Martin Mirchev, and Abhik Roychoudhury, 2026-05-12, Large Language Models in Software Security Analysis: LLMs can help tame the complexity at the root of many of today’s software security challenges, Communications of the ACM (CACM) June 2026 Vol 69 No. 6, pp 60-67, https://cacm.acm.org/research/large-language-models-in-software-security-analysis/
• [Xiao2026] Winnie Xiao, Tim Abbott, Nicholas Carlini, Newton Cheng, David Forsythe, Keane Lucas, Milad Nasr, and Shikhar Sakhuja, 2026-06-08, “Measuring LLMs’ impact on N-day exploits”, Anthropic, https://www.anthropic.com/research/n-days
• [Xiong2026] Yunpeng Xiong and Ting Zhang, 2026-01-30 (revised 2026-07-23), “Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering”, 35th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026), https://arxiv.org/abs/2601.22952
• [Veracode] Veracode, “What is AI Code Remediation?” https://www.veracode.com/security/what-is-ai-code-remediation/
• [Yan2026] Written by Eugene Yan and Henna Dattani, et al., 2026-05-27, “Using LLMs to secure source code”, Claude (Anthropic) Blog, https://claude.com/blog/using-llms-to-secure-source-code
• [ZeroDayClock] Zero Day Clock (website). https://zerodayclock.com/ especially https://zerodayclock.com/collapse
• [Zhang2024] Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, Abhik Roychoudhury, 2024, AutoCodeRover: Autonomous Program Improvement, https://arxiv.org/abs/2404.05427
• [Zhang2026] Cen Zhang, Younggi Park, Fabian Fleischer, Yu-Fu Fu, Jiho Kim, Dongkwan Kim, Youngjoon Kim, Qingxiao Xu, Andrew Chin, Ze Sheng, Hanqing Zhao, Michael Pelican, David J. Musliner, Jeff Huang, Jon Silliman, Mikel Mcdaniel, Jefferson Casavant, Isaac Goldthwaite, Nicholas Vidovich, Matthew Lehman, Taesoo Kim, 2026-05-29, “SoK: DARPA’s AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned”, https://arxiv.org/abs/2602.07666
• [Ziegler2026] Ziegler, Albert, 2026-05-12, “Mythos for Offensive Security: XBOW’s Evaluation” https://xbow.com/blog/mythos-offensive-security-xbow-evaluation
• [Zimmer2026] Derek Zimmer, 2026-06-16, Private Interview of Derek Zimmer by David A. Wheeler
• [Zorz2026] Zeljka Zorz, 2026-05-18, “AI is drowning software maintainers in junk security reports”, Help Net Security, https://www.helpnetsecurity.com/2026/05/18/problems-with-ai-assisted-vulnerability-research/