DeepMind's AlphaProof Code Formally Verifies Signal's Protocol, an AI First
roydanroy · x · 2026-11-11
Google DeepMind announced it used a new agentic framework, AlphaProof Code, to formally verify the actual code underlying Signal's cryptographic protocol — mathematically proving key security properties, a long-standing grand challenge in software security.
- AlphaProof Code is a multi-LLM agentic framework that splits verification like a research team: human experts decide what to prove alongside AI; a group of AI agents does the proving.
- Researchers first translated Signal's security goals into formal mathematical specifications with multiple models, with experts reviewing each one; agents powered by Gemini Carbon then generated over six million lines of Lean proof code.
This is the first time AI has formally verified a widely deployed cryptographic protocol at this depth, and the first time such a protocol implementation has been formally verified by any method, with or without AI.
More from Research
- Bronstein releases 78-page book: Mathematical Foundations of Geometric Deep Learning — caglar_ee · 2026-11-12
- Most biology AI models learn only one layer, and the big bet hinges on mapping — anshulkundaje · 2026-11-12
- Anthropic details agent memory: dreaming organizes Claude's memory, wiki+search hits 61% — RLanceMartin · 2026-11-12
- Talk preview: scaling 1,000 Fable 5.2 agents to formalize Fermat's Last Theorem — RLanceMartin · 2026-11-12
- Probing Qwen3 with a height ruler: each model's implicit "I" has a different height — Sauers_ · 2026-11-12
- Claude agent finds dwarf planet candidate in public sky data; $100K grants launched — jzlegion · 2026-11-12