AI-written patches are becoming hackers' attack maps
AI-written patches are becoming attack maps for hackers
Multiple studies and security conference reports show that AI-written patches are often incomplete, and instead mark out vulnerability locations and defensive approaches for attackers. Of the 6,080 AI patch candidates tested by 1Password Off-by-1 Labs, about half left at least one attack path; in the P2Patch benchmark, attack agents successfully bypassed patches in 41 of 101 cases. Anthropic researchers, using only public information from patch day, produced a working exploit within one hour of the Firefox fix landing; a Fudan University team's LLM-assisted binary comparison framework also confirmed that 26 of the patches for 62 closed-source applications could be bypassed, earning 19 CVEs. Epoch AI researchers used GLM 5.3 to simulate an ordinary attacker and, spending about $1,000 in API credits, broke every Firefox version between September 17 and October 26, leading Mozilla to decide it will no longer publish regression tests alongside security fixes.
Multiple studies and conference reports show that AI-written patches often leave attack paths; the article presents actionable remediation practices such as variant analysis and adversarial review.