Google DeepMind uses AI agents to formally verify Signal's core cryptographic code
Google DeepMind says its AlphaProof Code framework, which uses multiple AI agents, mathematically proved key security properties of the code underlying the Signal protocol. Human experts reviewed the security specifications, and the agents generated over six million lines of Lean, a language that checks code proofs. The agents flagged just one percent of the codebase for a human second look, and the verification took four weeks. Signal's Chief Technology Officer, Ehren Kret, said the work gives the company greater confidence in its code's privacy guarantees.