Google DeepMind researchers used agentic AI framework AlphaProof Code to verify the Signal protocol's cryptographic guarantees, in a four-week proof-of-concept (Lily Hay Newman/Wired)

Google DeepMind researchers utilized a new agentic AI framework called AlphaProof Code to formally verify the cryptographic guarantees of the Signal protocol. Conducted as a four-week proof-of-concept, the project served as independent validation for the cryptography used by platforms including WhatsApp, Google Messages, and the Signal app.

According to Wired, the work demonstrates DeepMind's formal verification capabilities. While formal verification uses mathematics to validate that software functions as intended without critical vulnerabilities, the process was traditionally time-consuming for humans to perform. Agentic AI can significantly reduce the time required for developing proofs.

Wired notes that this specific analysis was limited in scope and did not formally verify the entire Signal mobile app. DeepMind researchers emphasized that the findings represent a single milestone in a larger process.

Brief written by urgent.news from Techmeme, Wired, Dev.to — 3 reports on this story. Machine-written — may contain errors; check the original before relying on it.