Anthropic 推出 FlashProve：可验证 LLM 推理来源的密码学方法
Anthropic 开源了 FlashProve，用密码学证明回复真的出自某个模型，还能防聊天劫持，做安全评估的可以看看。
Anthropic 发布名为 FlashProve 的研究项目，基于已有密码学技术，让开发者验证某条回复确实来自指定 AI 模型。相比以往的开源方法，FlashProve 在效率上有明显提升，代码已在 GitHub 开源。论文合作者包括 Alessandro Chiesa、Giacomo Fenzi 等。应用场景包括防止攻击者劫持聊天会话，以及让安全评估方确认所测试的模型与实际服务用户的模型一致。
New Anthropic research: progress on provable inference for large language models. Here, we introduce FlashProve. Building on established cryptographic techniques, FlashProve allows developers to verify whether a given response came from a given AI model. It’s substantially more efficient than prior open-source methods for doing so. These proofs have a range of applications. They can, for instance, make it harder for attackers to hijack a chat, or enable safety evaluators to verify that the model they’re testing is the same one being served to customers. For our full write-up, see here: anthropic.com/research/prova… Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that end, we're open-sourcing FlashProve’s code, here: github.com/anthropics/Fla… We’re grateful to our collaborators: Alessandro Chiesa, @GiacomoFenzi , @gwberg95 , @miranda__christ , Rahul Dalal ( rdalal.github.io ) and Ben Mayer ( @transmissions11 ). 💬 133 🔄 77 ❤️ 1158 👀 60045 📊 255 ⚡
