Science & Tech · AI · 3 hrs ago

Google DeepMind Uses AI to Verify Key Signal Protocol Guarantees

Google DeepMind Uses AI to Verify Key Signal Protocol Guarantees

Google DeepMind used AI to mathematically verify key guarantees in the Signal protocol.

The protocol’s encryption helps protect messages on services including Signal, Google Messages and WhatsApp.

Researchers found no new vulnerabilities in the parts they examined.

When they tested older versions with known, fixed flaws, the AI identified them and showed those versions could not be verified.

The work covered parts of the protocol, not the entire Signal app.

The researchers are releasing their specification and proof to support further verification work.

Whether AI can verify much larger software systems at a workable cost remains an open question.

1 source

Related

What people are saying

Swarat ChaudhuriDeepMind research scientist
We are very excited by this result, but there is a long distance to go before we are able to scale this to all the software of the world, and we want to do that.
via Wired
Ehren KretSignal chief technology officer
While prior formal verification focused on smaller portions of the code, Google DeepMind's approach enables significant expansion
via Wired
As AI-driven security threats grow, rigorously verifying the Signal protocol implementation gives us even greater confidence in our code's privacy guarantees.
via Wired
Pushmeet KohliGoogle Cloud chief scientist and DeepMind vice president of research
If you can now verify the correctness of these implementations, then you can rest easy
via Wired