跳到正文
DEV Community· Abhishek Jambla·· 18 天前AI 評分57

FlashProve 以加密證明核實 API 回覆所用的 AI 模型

FlashProve: Proving Which AI Model Actually Answered

AI 導讀

Anthropic 的 FlashProve 是一個開源研究原型,透過加密證明核實 API 回覆是否由指定模型產生。提供者的 GPU 會為每次回覆生成證明,驗證該模型確實輸出了那些 token;用戶可用普通 CPU 驗證,無須 GPU 或取得模型權重。

正文

Cover image for FlashProve: Proving Which AI Model Actually Answered

Abhishek Jambla

You call an AI API. How do you know the model that replied is the one you asked for? Today, you don’t. Anthropic’s FlashProve (open source, Apache 2.0) is a research prototype that fixes this with a cryptographic proof.

How it works

Commit: The provider publishes a short “fingerprint” of its model weights. The weights stay secret.
Prove: For each reply, the provider’s GPU creates a proof that the committed model produced those exact tokens.
Verify: You check the proof on a normal CPU. No GPU, no weights needed.

Numbers (Llama 4 Maverick, 400B)

About 110 tokens/sec on one H100
Proof size ~19 MB; check time ~17 sec
Proving costs 70-95x the GPU time of normal serving

Why it matters

Catch secret model swaps by routers or providers
Spot tampered responses
Give auditors and regulators real proof

Limits

Only 1,024 tokens of context
Proves an integer version with greedy decoding
Hides weights, not architecture
Prototype: not maintained, no deployment plans

Media
Visual aid: Interactive Lean theorem visualizer from the FlashProve repo, which shows the security claims being checked

References & Credits

Anthropic, Progress on provable inference (Roy Rinberg, Alex Allain and co-authors from EPFL, MIT, StarkWare and Succinct)
FlashProve on GitHub (Apache 2.0)
TechCrunch, Russell Brandom
Interesting Engineering, Neetika Walter

來源:DEV Community · dev.to