Anthropic Open-Sources FlashProve for Verifiable LLM Inference
Cryptographic proof of model identity addresses a gap that API-level assurances cannot close: evaluators and enterprises can now independently check what they are actually serving or testing. The open-source release means anyone can integrate verification today rather than wait for vendor-side guarantees. Teams running safety evaluations or deploying LLMs in security-sensitive workflows are the immediate beneficiaries.
Anthropic introduced FlashProve, a cryptographic method that lets developers verify whether a given response actually came from a given AI model. The company says it is substantially more efficient than prior open-source provable inference methods. Applications include preventing chat hijacking by attackers and letting safety evaluators confirm the model being tested matches the one served to customers. Anthropic has open-sourced FlashProve's code on GitHub, with collaborators including Alessandro Chiesa and Giacomo Fenzi.
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 ⚡
