Skip to content
EventUpdating

Study says AI-written patches are often incomplete fixes, instead becoming attack roadmaps

1 reports1 reporting sourcesplus 2 outlets covering itLatest report

Start here

AI overview

Multiple studies and security conference reports show that AI-written patches are often incomplete fixes, instead marking 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 diffing framework confirmed 26 bypassable patches out of 62 closed-source applications' patches, obtaining 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, prompting Mozilla to decide to stop publishing regression tests alongside security fixes.

Generated by AI from reports · Updated 3 days ago

Attention and developments

Attention, hourly

Now 42, -1% in 24 hours·Peak 48 (Nov 17 01:00)

Nov 17Nov 18Nov 19Nov 20Now 42

Progress timeline

Nov 17
Nov 16
  1. CSO OnlineSelected
    AI-written patches are becoming hackers' attack maps

    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.

Related discussion

Total 10 items

Attention trend

New sources per day

10 in 5 days·most 4 (Nov 17)·today 0

  • Nov 16: 3 new sources (2 outlets, 1 accounts)
  • Nov 17: 4 new sources (0 outlets, 4 accounts)
  • Nov 18: 2 new sources (0 outlets, 2 accounts)
  • Nov 19: 1 new sources (1 outlets, 0 accounts)
  • Nov 20: 0 new sources (0 outlets, 0 accounts)

Hourly attention

Current attention 42·Peak in the comparable period 48 (Nov 17 01:00)·Change over the comparable past 24 hours -1%

0204060Nov 1623:00Nov 1800:00Nov 1901:00Nov 2002:00