OpenAI 与 FMF 发布前沿网络威胁越狱评级框架
OpenAI 与 Frontier Model Forum（FMF）及其成员公司合作推出新框架，用于判断绕过 AI 系统安全防护何时可能造成严重网络危害，并据此优先加强防护。OpenAI 国家安全政策负责人 Sasha Baker 称，该框架是评估和比较网络越狱严重程度（包括其解锁的能力及可用性）的共同方法论的重要一步。
OpenAI· @OpenAI · X·2026-11-07 03:58· 38 分钟前AI 评分48
AI 导读
OpenAI 与 Frontier Model Forum（FMF）及其成员公司合作推出新框架，用于判断绕过 AI 系统安全防护何时可能造成严重网络危害，并据此优先加强防护。OpenAI 国家安全政策负责人 Sasha Baker 称，该框架是评估和比较网络越狱严重程度（包括其解锁的能力及可用性）的共同方法论的重要一步。
正文 · 原文
We partnered with @fmf_org and its member firms on a new framework to help identify when bypassing an AI system's safeguards could enable serious cyber harm, and prioritize stronger protections.
"...This framework is 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. Shared approaches like this can help the AI and security communities build a clearer evidence base and prioritize improvements to safeguards." - OpenAI's Sasha Baker, Head of National Security Policy
来源：OpenAI · x.com
来源：RadarAI · aihot.news