DeepMind's AlphaProof Code formally verifies Signal protocol at machine-code level
tianyin_xu · x · 2026-11-11
A Google DeepMind team says it has cracked a major challenge in software engineering and security: formally verifying a real-world implementation of the Signal cryptographic protocol at the machine-code level. The proof was produced with AlphaProof Code, their new AI framework for formal specification and verification.
A paper, the Lean codebase, and a DeepMind blog post were released alongside the announcement. Team members include Tej Chajed, Jonathan Katz, and Pushmeet Kohli. The author notes they began working on formal verification 20+ years ago as a grad student — marking a milestone for AI-driven verification of real cryptographic implementations.
More from coding & agent
- Ethan Mollick lets a swarm of agents argue their way into building a fantasy transport sim — emollick · 2026-11-11
- Margin: open-source Mintlify-compatible docs framework ships free hosting built for AI agents — ycombinator · 2026-11-11
- Netlify launches Servers: long-lived WebSocket servers in the same deploy as your site — thisiskp_ · 2026-11-11
- Duke and Princeton paper: 10 small parallel agent teams beat best-of-N and one giant team — rohanpaul_ai · 2026-11-11
- ERP team open-sources Dory docs-with-MCP and UX ShadCN theme library for free — hkdeman · 2026-11-11
- LangChain's OpenWiki builds citation-based evidence graphs for agent memory — a leaner GraphRAG alternative — JeremyCMorgan · 2026-11-11