Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
2026-11-11 · Google DeepMind
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
Google DeepMind is sharing a milestone in software security: researchers guided AI agents to mathematically prove key security properties of the actual code underlying the Signal protocol, which protects billions of private conversations in apps such as Signal and Google Messages. The work used AlphaProof Code, a new agentic framework for formal verification at unprecedented depth that combines human expertise with AI agents. Formal verification—mathematically proving code runs correctly without flaws—is the highest standard of security assurance, but it is difficult and labor-intensive.
A first at this depth
According to Google DeepMind, this is the first time AI has been used to formally verify a widely deployed cryptographic protocol at this depth. It is also the first time the implementation of a widely deployed protocol like this has been formally verified by any method, with or without AI.
How Signal was verified
AlphaProof Code is a multi-LLM agentic framework that divides formal verification the way a research team would: human experts work with AI to decide what to prove, and a group of AI agents does the work.
- Researchers collaborated with a mix of models to translate Signal’s security goals into formal mathematical specifications, with human experts reviewing every one.
- Agents powered by Gemini Carbon produced the proofs, generating more than six million lines of Lean, a computer language that mathematically proves the accuracy of code.
- The agents then audited the proof and highlighted areas needing a second human look—only about one percent of the codebase. Because Lean automatically checks the rest, experts could focus their review where human judgment matters most.
From design to running code
Cryptographic protocols underpin nearly all digital communication, from online banking to web browsing, and a single flaw can expose millions of people at once. Experts have spent decades formally analyzing protocols, but most protocol verification stops at the design level. The agents went further, proving that the compiled code fulfills key security properties—such as keeping messages protected before and after a device is temporarily compromised—down to the exact code running on devices. Real-world vulnerabilities often hide in the gap between design and implementation, and bridging that gap makes the proofs vastly more complex. Even so, verification took just four weeks, compared with a task that historically takes expert teams years. The result proves that Signal’s core cryptographic code delivers the security protections specified by the experts.
Testing whether it can spot bugs
To confirm that AlphaProof Code can tell correct code from buggy code, the team reintroduced two real, previously fixed bugs into an isolated version of Signal’s code. In both cases, the system produced a machine-checked proof that the buggy version was insecure. In AlphaProof Code, AI agents help users write a specification and then autonomously prove that the implementation meets it. Every proof is checked by Lean.
Industry reaction and next steps
Ehren Kret, Chief Technology Officer of Signal, said that while prior formal verification focused on smaller portions of code, Google DeepMind’s approach enables significant expansion. He called using AI agents to translate live code into valid Lean theorems a major breakthrough, adding that as AI-driven security threats grow, rigorously verifying the Signal protocol implementation gives greater confidence in its privacy guarantees.
Google DeepMind says the achievement shows how AI can bring elite security assurance to businesses, governments, and critical infrastructure, helping defend against agent-driven cyber threats. Verifying Signal’s core cryptography lays groundwork to secure other vital systems, from medical device firmware to power grid software. Scaling these techniques requires continued research. Paired with automated defense agents such as CodeMender, formal verification can help counter the speed and scale of modern cyber threats and create software with mathematical proof that its protections work. Google DeepMind is open-sourcing its formal verification artifacts for community use.