OpenAI 与 FMF 及其成员机构合作推出评估 AI 网络越狱危害的新框架
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 https://t.co/epOq98YPau
OpenAI 与 FMF 及其成员机构合作发布新框架，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。该框架旨在为评估和比较网络越狱的严重程度提供共同方法，包括其解锁的能力及被利用的难易程度。OpenAI 国家安全政策负责人 Sasha Baker 称，这类共享方法可帮助 AI 与安全社区建立更清晰的证据基础。
粉丝 552万
认证：X 认证的官方组织
OpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6LgzPA
- 浏览
- 21万
- 点赞
- 1084
- 评论
- 300
- 分享
- 79
- 收藏
- 143
数字来自平台，为最近一次抓取时的数据。
来源：X · OpenAI · x.com