OpenAI 联合 Frontier Model Forum 推出网络越狱严重性评估框架
OpenAI 和 Frontier Model Forum 出了个评估越狱严重程度的框架，做 AI 安全防护的同行可以直接参考这套标准。
OpenAI 与 Frontier Model Forum 及其成员公司合作发布了一套新框架，用于判断绕过 AI 系统安全防护的行为是否可能造成严重网络危害。该框架提供了一个共同方法来评估和比较网络越狱的严重程度，包括越狱解锁的能力以及被利用的难易程度。OpenAI 国家安全政策负责人 Sasha Baker 表示，这类共享方法能帮助 AI 与安全社区建立更清晰的证据基础，并优先改进安全防护措施。
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 frontiermodelforum.org/updates/introd… 💬 188 🔄 35 ❤️ 525 👀 72640 📊 194 ⚡
