Anthropic 发布 FlashProve，可验证模型回复来源并开源代码
New Anthropic research: progress on provable inference for large language models.
Anthropic 公布可验证推理方向的新研究 FlashProve，基于已有密码学技术，让开发者验证某条回复是否来自指定 AI 模型，并称其效率明显高于此前的开源方法。该证明可用于增加攻击者劫持对话的难度，也能让安全评估者确认被测模型与对外服务的模型一致。Anthropic 已开源 FlashProve 代码，并列出 Alessandro Chiesa 等合作者。
推荐理由
AI 评分 61
Anthropic 开源 FlashProve，让开发者能验证某条回复是否出自指定模型，并称其效率明显高于此前的开源方法。
主题
正文
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: https://t.co/OIZWPb6QZa
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: https://t.co/7ky3Ir8V06
We’re grateful to our collaborators: Alessandro Chiesa, @GiacomoFenzi, @gwberg95, @miranda__christ, Rahul Dalal (https://t.co/pjWKLHWXyz) and Ben Mayer (@transmissions11).