BriefsNewsAvailable now1 min read

Google DeepMind uses Gemini AI to verify the Signal protocol

AlphaProof Code combines human expertise with AI agents to mathematically prove software security properties.

Google DeepMind uses Gemini AI to verify the Signal protocol — image from Google DeepMind
Image: Google DeepMind

Summary

Google DeepMind released AlphaProof Code, an agentic framework for formal verification of software. The system combines human expertise with AI agents powered by Gemini Carbon to generate mathematical proofs in the Lean language. Researchers used the framework to verify the Signal cryptographic protocol in four weeks.

What changed

  • Introduced AlphaProof Code, a framework combining human expertise and AI agents for formal verification.
  • Used Gemini Carbon-powered agents to generate over six million lines of Lean code for proof.
  • Audited proofs automatically, leaving just one percent of the codebase for human review.
  • Open-sourced all formal verification artifacts for community use.

Availability

Available now

“We are open-sourcing our formal verification artifacts for community use.”

Founder takeaway

The open-sourced artifacts are available for community use. Teams building high-security software should examine the release to see how automated verification works in practice.

Source

Google DeepMindFormal Verification of Signal’s Protocol with Gemini — Google DeepMind

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. Google brings the Gemini app to low-memory Android devices — image from Google AI

    NewsAvailable now

    Google brings the Gemini app to low-memory Android devices

    Google re-architected the Gemini app so it can run on eligible Android Go edition phones.

    Google AI1 min read

  2. Fireworks AI benchmarks the MiniMax M3.1 Flash AI model — image from Fireworks AI

    NewsAvailable now

    Fireworks AI benchmarks the MiniMax M3.1 Flash AI model

    Fireworks AI compares the MiniMax M3.1 Flash AI model against closed alternatives and tests how combining models changes costs and coding completions.

    Fireworks AI1 min read

  3. Google adds temporary threads to AI Mode in Search — image from Google Search

    NewsRolling out

    Google adds temporary threads to AI Mode in Search

    Google introduced temporary threads in AI Mode so users can ask questions without saving them to their history or affecting recommendations.

    Google Search1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.