OpenAI and fmf unveil framework to grade when AI jailbreaks enable serious cyber harm
OpenAI · x · 2026-11-07
OpenAI partnered with fmforg and its member firms on a new framework to identify when bypassing an AI system's safeguards could enable serious cyber harm, and to prioritize stronger protections. Sasha Baker, OpenAI's Head of National Security Policy, called it an important step toward a common methodology for evaluating and comparing the severity of cyber jailbreaks, including the capabilities they unlock and how readily they can be used, helping build a clearer evidence base for the AI and security communities.
More from Safety
- Researcher says stock GLM 5.3 refuses often; abliterated version shipped same month at same price — matthew_d_green · 2026-11-07
- Anthropic's IPO prospectus warns its technology could pose 'catastrophic or existential risks' — jeremyakahn · 2026-11-07
- AI analysis of 111 model cards: Chinese open-weight frontier models ship with almost no safety evals — ChenhaoTan · 2026-11-07
- Gladstone AI CEO: Washington won't slow AI until an 'AI Chernobyl' strikes — AaronBergman18 · 2026-11-07
- Census swaps AI for SI in survey to comply with executive order, 'don't know' answers jump — TaniaBabina · 2026-11-07
- Xbow on offensive security model evals: the best model depends on your budget — moyix · 2026-11-07