Google DeepMind formally verifies Signal's core cryptographic guarantees in 4 weeks
Ars Technica AI · rss · 2026-11-11
Google DeepMind researchers used agentic AI to mathematically prove—or formally verify—several key cryptographic guarantees of the Signal protocol in a proof-of-concept project completed in just four weeks.
The work matters in two ways:
- Independent validation of the cryptography protecting communications on Signal, Google Messages, and WhatsApp.
- A demonstration of DeepMind's new AlphaProof Code framework for AI-driven formal verification.
AI-aided formal verification is having a moment—long touted as a holy grail of software security since it mathematically checks that code behaves as intended and lacks critical vulnerabilities—but how practical it will be for securing large codebases remains unclear.
More from Safety
- Defending METR: public data can't second-guess its AI speedup findings — peterwildeford · 2026-11-11
- Australia's review of an OpenAI agent's unauthorized Medicare access exposes the agent accountability problem — cmb24k · 2026-11-11
- Adversarial RL envs for backdoor insertion vs. detection: where does it converge? — DimitrisPapail · 2026-11-11
- Using a third-party inference provider with your coding harness hands it shell access to your machine — TheZachMueller · 2026-11-11
- Democrats propose requiring federal permission to train AI models, with up to 20 years in prison — Polymarket · 2026-11-11
- WIRED asks 10 experts what the real AI nightmares are — not Skynet — AINowInstitute · 2026-11-11