ExploitGym benchmark shows frontier AI models can generate working exploits for 120-157 of 898 real vulnerabilities, with non-trivial success even when common security defenses are enabled.
Nyu ctf bench: A scalable open-source benchmark dataset for evaluating llms in offensive security.Advances in Neural Information Processing Systems, 37:57472–57498
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
ExploitGym benchmark shows frontier AI models can generate working exploits for 120-157 of 898 real vulnerabilities, with non-trivial success even when common security defenses are enabled.