Anthropic releases FlashProve, which can verify the source of model responses and open-sources the code
Anthropic has announced FlashProve, a new research direction in verifiable inference. Built on existing cryptographic techniques, it lets developers verify whether a given response came from a specified AI model, and Anthropic says it is significantly more efficient than previous open-source methods. The proof can be used to make it harder for attackers to hijack conversations, and it also allows safety evaluators to confirm that the model being tested is the same as the model serving the public. Anthropic has open-sourced the FlashProve code and lists collaborators including Alessandro Chiesa.
Why read this
AI score 61
Anthropic has open-sourced FlashProve, enabling developers to verify whether a given response came from a specified model, and says it is significantly more efficient than previous open-source methods.
Topics
Body
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).