Anthropic 研发 FlashProve 系统，用密码学证明 AI 模型身份
原标题：Anthropic is working on a system to prove AI models’ identity
AI 摘要
Anthropic 于周二发布博客，宣布正在研发开源系统 FlashProve，通过密码学证明验证某段输出确实来自特定 AI 模型，类似邮件数字签名，可防止模型冒充。系统要求 AI 实验室发布不泄露模型权重的模型「指纹」，并设计为轻量级、可在本地设备验证，从而也适用于闭源商业模型。研究者同时公开了技术规范与部分代码，但强调研究仍在进行，暂无在 Anthropic 或其他实验室部署的计划。
正文节选
Anthropic is working on an open-source system to verify which AI model produced a given output, according to a blog post published Tuesday. The system, called FlashProve, is built to provide what researchers call “provable inference” – a cryptographic proof, essentially a mathematical guarantee, that a given output came from a specific model. It’s meant to let users confirm that the answer they received really came from the model they think they’re using. Similar to cryptographic email signature