Anthropic open-sources FlashProve: cryptographic proofs that a response came from a given model
AnthropicAI · x · 2026-11-04
Anthropic announced FlashProve, new research on provable inference for LLMs. Building on established cryptographic techniques, it lets developers verify whether a given response actually came from a given AI model, and is substantially more efficient than prior open-source methods.
Use cases include making it harder for attackers to hijack a chat, and letting safety evaluators confirm the model being tested is the same one served to customers. Anthropic has open-sourced the code, with collaborators including cryptographer Alessandro Chiesa.
Related event: Anthropic Open-Sources FlashProve: zkSNARK-Provable LLM Inference(24 posts)→
More from Safety
- ARTEX red team tool's Docker image found to contain an unauthorized backdoor — Kyrannio · 2026-11-04
- India's CERT-In gets Anthropic's Claude 'Mythos' to probe cybersecurity flaws, skeptics unimpressed — kingslyj · 2026-11-04
- Ternary Logic proposal: enforcing AI safety at the architecture level — MoralLogs · 2026-11-04
- Cambridge's David Krueger: A global AI pause needs coordination, not trust — DavidSKrueger · 2026-11-04
- Security advisory: run AI agents in managed cloud environments, not employee endpoints — amasad · 2026-11-04
- Man who siphoned 4M accounts' credits from AI platform reselling them gets suspended sentence — 葬AI · 2026-11-04