OFFICIAL Written by GPN · Nov 10, 2026, 7:54 AM ET · · Tech
Google DeepMind has formally verified the code behind Signal's cryptographic protocol using AI, in what it calls a first for software security.
The work was done with AlphaProof Code, a new agentic framework for formal verification — mathematically proving that code does what it is supposed to do. DeepMind says it is the first time AI has formally verified a widely deployed cryptographic protocol at this depth, and the first time the implementation of such a protocol has been formally verified by any method at all.
Signal's protocol protects private conversations in apps including Signal and Google Messages. Formal verification is the highest standard of security assurance, but it is difficult and labour-intensive, and most previous work has stopped at verifying a protocol's design rather than its code.
AlphaProof Code splits the job the way a research team would. Human experts worked with AI models to turn Signal's security goals into formal mathematical specifications, reviewing every one. AI agents powered by Gemini Carbon then produced the proofs, writing more than three million lines of machine-checked proof in Lean, a language for mathematically proving code correct. The agents then audited their own work and flagged just one percent of the codebase for a second look by a human, with Lean automatically checking the rest.
The verification covers the key security properties of Signal's core cryptography, including keeping messages protected before and after a device is temporarily compromised. DeepMind says the whole process took four weeks, where the same work has historically taken expert teams years.
To test that the system can tell good code from bad, the researchers reintroduced two real, previously fixed bugs into an isolated copy of Signal's code. In both cases, AlphaProof Code produced a machine-checked proof that the buggy version was insecure.
DeepMind is open-sourcing its formal verification artifacts for community use. It says verifying Signal's core cryptography lays the groundwork for securing other vital systems, from medical device firmware to power grid software, and that the approach could bring elite security assurance to businesses, governments and critical infrastructure as AI-driven threats grow.