AlphaProof Code verifies Signal protocol security properties
Google DeepMind used its AlphaProof Code framework to formally verify selected security properties in the compiled implementation of the Signal protocol. Human experts defined the goals, Gemini Carbon-powered agents generated more than six million lines of Lean proofs, and the agents flagged about 1% of the code for additional human review, according to the company. The four-week project found no new vulnerabilities in the examined portions and correctly rejected buggy historical implementations, but the researchers said prior formal-verification work helped them begin.
The project demonstrates a practical human-AI workflow for mathematical verification of deployed cryptographic code, while remaining a property-specific proof rather than a security audit of the entire Signal application.
How Google DeepMind researchers built a new agentic framework that formally verified the code of Signal’s cryptographic protocol — long considered to be a grand security challenge
Today, we’re sharing a milestone in software security long considered to be a grand security challenge: Google DeepMind researchers guided AI agents to mathematically prove key security properties of the actual code underlying the Signal protocol, the technology that protects billions of private conversations in apps like Signal and Google Messages.
This breakthrough discovery was made using AlphaProof Code, a novel 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; however, it is difficult and often labor-intensive.
Our work marks the first time AI has been used to formally verify a widely deployed cryptographic protocol at this depth. It's 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 we verified Signal
AlphaProof Code is a multi-LLM agentic framework that splits the work of 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 it.
#Google DeepMind#AlphaProof Code#Signal Protocol#Gemini Carbon#Lean#Signal#WhatsApp#Google Messages