KEY POINTS
- Google DeepMind used agentic AI to mathematically prove several key cryptographic guarantees of the Signal protocol in about four weeks.
- No new vulnerabilities turned up, but the tool flagged known, long-fixed flaws in older Signal versions and showed they could not be verified.
- Google did not disclose the cost of the work or say whether it plans a commercial verification product.
Google DeepMind researchers have used agentic AI to formally verify a number of the cryptographic guarantees in the Signal protocol, Ars Technica reported. Formal verification means using mathematics to prove that software behaves as intended, rather than relying only on testing.
