创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

FMF推出AI越狱评级框架

AI 总结

Frontier Model Forum发布了1.0版《越狱评级框架》,该提案参考CVSS,按能力增益、能力范围、部署难度和发现难易度对LLM越狱进行评级。据Tom’s Hardware报道,框架将严重程度与可能性结合,形成从低到严重的最终评级,能力增益得分还会约束其他维度的评分。FMF称该体系有望成为开发补丁团队可采用的跨厂商标准,但1.0版仍在评审中,并建议在12月21日前收集意见期间暂勿依赖该体系。

深度见解

FMF希望用统一方法比较LLM越狱,并衡量其能否让模型获得现有工具之外的作战能力。

In recent months, high-profile headlines about AI models letting loose from their safeguards dominated headlines. Now, the Frontier Model Forum (FMF) has released a new Jailbreak Rating Framework that aims to track how easy it might be for a given AI model to get around safeguards. The framework also estimates the scale of the collateral damage, should an AI model wreak cyber-havoc across the internet.

The project started in 2023 with the support of four founding companies: Anthropic, Google, Microsoft, and OpenAI. The published Jailbreak Rating Framework is a rough analog to the well-known CVSS security rating system, but specifically targeted at classifying the type and severity of LLM jailbreaks across various axes and multiple frontier LLM providers.

Many AI companies and evaluation entities already have their own rating systems, but the FMF intends for its scale to be a cross-vendor standard that teams developing patches can rely on.

The FMF's approach is to have a classification method for jailbreaks that can make a model perform cyber-warfare operations beyond what's already out, across both the regular and black market. Version 1.0 of the proposal is a work-in-progress, and the group is taking comments and suggestions on it until December 21, noting that relying on its system in the meantime is inadvisable.

#Frontier Model Forum#Jailbreak Rating Framework#Anthropic#Google#Microsoft#OpenAI

原文约 4 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。