重點導讀
OpenAI 與 fmf_org 及其成員公司共同推出一套評估 AI 系統安全漏洞的新框架，旨在判斷繞過安全機制可能造成的嚴重網路風險。
- 框架功能：提供一套標準化方法，評估「cyber jailbreak」的嚴重程度、解鎖能力與易用性。
AI 伴隨問答
針對這篇報導有疑問？可直接點選快捷問題或向 AI 追問背景脈絡與技術細節：
OpenAI@OpenAI
·2 小時前
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
推文來源 · X (Twitter)在 X 參與討論