Vulnerability repair

PatchBench, from the University of Maryland's AI Security Lab, evaluates 11 patching agents, including the top three AIxCC systems, on 213 C/C++ tasks whose true fixes lie outside the crash stack, using vulnerability transplant and code mutation to limit memorization. It finds that accepting a patch because the original proof-of-concept no longer crashes inflates solve rates by 1.83x on average, and that about 25% of agent patches closely resemble historical developer fixes.

Google introduced Gemini 3.8 Flash Cyber, a cybersecurity-tuned model with more permissive cyber mitigations, available only to trusted defenders through a new Fairwind Program. Google says it prioritized vulnerability fixing over exploitation and reports 47.2% pass@1 on Collinear's CWE-Bench patching benchmark, over 70% on an internal 20-language discovery benchmark, and 2.6 times more correct Chrome patches than larger commercial models.

The Commission presented an action plan responding to advanced AI models that can both improve and undermine cybersecurity. It plans an EU capacity to evaluate AI models, a European blueprint for structured access to advanced AI capabilities developed with ENISA, a secure ENISA-JRC platform to test AI for cybersecurity, AI-assisted vulnerability fixing, and a campaign to secure critical open-source software. ENISA published its own recommendations for the frontier AI era the same day.

The heads of the Five Eyes cyber agencies issued a joint statement that AI is rapidly transforming cyber risk and that organizations must act within months, not years. They ask leaders to reduce attack surface, accelerate patching as exploitation windows shorten, replace unsupported legacy systems, strengthen identity controls, and prepare for incidents.

Executive Order 14409 directs Treasury, NSA and CISA to develop a classified benchmarking process to assess advanced cyber capabilities of AI models and designate covered frontier models, with a voluntary framework for pre-release government and trusted-partner access. It also orders an AI cybersecurity clearinghouse to coordinate vulnerability scanning, validation and remediation with industry, and states it does not create mandatory licensing or pre-clearance.

Anthropic reports that about 50 Glasswing partners used Claude Mythos Preview to find more than ten thousand high- or critical-severity vulnerabilities, and that its own scan of over 1,000 open-source projects produced 6,202 model-estimated high/critical findings. Of 1,752 assessed, mostly by six independent firms, 90.6% were true positives; Anthropic estimates 530 high/critical bugs disclosed, of which 75 were patched, and says triage and patching capacity, not discovery, is the bottleneck.

Researchers led by Georgia Tech released OSS-CRS, a locally deployable framework for running and combining AIxCC cyber reasoning systems, noting that all seven open-sourced finalist systems depended on competition cloud infrastructure that no longer exists. Porting the winning Atlantis system, they found 10 previously unknown bugs (three high severity) in 8 OSS-Fuzz projects; OpenSSF welcomed OSS-CRS into its AI/ML Security Working Group in April 2026.

OpenAI renamed Aardvark to Codex Security and opened a research preview to ChatGPT Pro, Enterprise, Business and Edu customers. OpenAI reports that in 30 days it scanned over 1.2 million commits in its beta cohort and flagged 792 critical and 10,561 high-severity findings, that beta changes cut false positives by more than 50%, and that its open-source reports led to 14 CVEs.

Anthropic released Claude Code Security as a limited research preview for Enterprise and Team customers, with expedited free access for open-source maintainers. The tool reasons about data flow across a codebase, re-examines each finding in a multi-stage verification pass, assigns severity and confidence ratings, and proposes patches that are applied only with human approval.

A systematization-of-knowledge paper by organizers and competitors analyzes AIxCC's design, the seven finalist architectures and results beyond the scoreboard. It reports that system stability and accuracy penalties decided rankings, that LLM-based systems found vulnerabilities a fuzzing baseline missed, and that among patches passing all automatic validation, manual review found semantic errors in 38-46% from baseline agents; the top two systems had 83.8% and 79.2% competition-scored patch accuracy.

Anthropic's Frontier Red Team reports that Claude Opus 4.6, run in a VM with standard tools but no custom harness, found and validated more than 500 high-severity vulnerabilities in open-source software, focusing on memory corruption that can be confirmed with sanitizers. Every bug was validated before reporting, initially by Anthropic researchers who also wrote patches and later with external researchers; examples include Ghostscript, OpenSC and CGIF.

OpenAI announced Aardvark, a GPT-5-powered agent in private beta that builds a threat model of a repository, scans commits, tries to trigger suspected flaws in a sandbox, and attaches Codex-generated patches for human review. OpenAI reports 92% recall on known and synthetically introduced vulnerabilities in its 'golden' repositories and ten CVEs from open-source scanning, and planned pro-bono scanning for some non-commercial projects.

Google DeepMind introduced CodeMender, an agent built on Gemini Deep Think models that combines static and dynamic analysis, fuzzing, differential testing and SMT solvers with LLM-based critique to generate and validate security patches. DeepMind reports 72 security fixes upstreamed to open-source projects over six months, all reviewed by human researchers before submission; in May 2026 Google said it would fold CodeMender into its enterprise agent platform.

Anthropic reports that a small team focused Claude Sonnet 4.5 training on finding and patching vulnerabilities and on testing simulated security infrastructure, while avoiding enhancements that clearly favour offence. It reports Sonnet 4.5 results on Cybench and CyberGym, a preliminary patching study in which 15% of patches were judged semantically equivalent to human references, and invites work on SOC and SIEM automation.

DARPA reports that seven finalist cyber reasoning systems analyzed over 54 million lines of code, found 54 unique synthetic vulnerabilities in 63 challenges and patched 43, and found 18 real non-synthetic vulnerabilities with 11 patches. Team Atlanta won $4 million, Trail of Bits $3 million and Theori $1.5 million; DARPA and ARPA-H added $1.4 million for real-world integration and four systems were open-sourced on the day.

SEC-bench uses multi-agent scaffolding to construct reproducible vulnerability instances with test environments and validated patches from real projects, at about $0.87 per instance. The authors report that LLM agents reached at most 18.0% on proof-of-concept generation and 34.0% on vulnerability patching.

BountyBench, from Stanford-led researchers, builds 40 bug bounties across 25 real-world systems into 120 Detect, Exploit and Patch tasks with dollar values attached. In the first version the best Detect score was 5%, while OpenAI Codex CLI and Claude Code scored 90% and 87.5% on Patch, well above their Exploit scores. A July 2025 revision with more agents reported Codex CLI with o3-high at 12.5% on Detect and 90% on Patch.

Meta introduced AutoPatchBench, part of CyberSecEval 4, with 136 fuzzing-identified C/C++ vulnerabilities and verified fixes, plus a 113-case Lite subset with single-function root causes. Patches are checked by build and crash reproduction, then fuzzing and white-box differential testing; Meta's reference agent generated crash-stopping patches in about 60% of cases, but only 5-11% passed the stricter checks.