CyberBinGym tests AI agents exploiting binary patch diffs
The strongest agent recovered the flaw in 88 percent of 100 tasks and produced a working exploit in 20 percent.
Stories per day · 30 days
6 stories, newest first · one card per story
Stories tagged #exploit-generation
Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks
AI attack and repair performance varies sharply on nonpublic vulnerabilities, and one fix often fails later tests.
Anthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploits
Anthropic says open-weight GLM-5.3 nearly matches Claude Mythos Preview at building software exploits.
GLM-5.3 and the spread of advanced cyber capabilities
Anthropic finds Zhipu's open-weight GLM-5.3 autonomously builds end-to-end exploits and its safeguards can be bypassed 64-100% of the time.
Security through obscurity is dead, and AI delivered the fatal blow
AI agents are killing security through obscurity, accelerating vulnerability discovery and patch-gap exploitation, experts warn, with OT/ICS systems most at risk.
3
Most of the bugs Claude Mythos found have never been checked by a human
Echo's analysis found only 1,900 of 23,019 Claude Mythos-found vulnerabilities were externally reviewed, 90.8% held up, but the model overstated most severities.