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.
SECODEPLT: A unified benchmark for evaluating the security risks and capabilities of code genAI
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.