Formal Verification of Signal’s Protocol with Gemini

AlphaProof Code: Verifying Signal’s Security at the Machine-Code Level

We introduce AlphaProof Code, a multi-agent AI framework for formal software specification and verification that we used to prove key security properties of libsignal, the Signal protocol’s reference implementation, at the machine-code level. AlphaProof Code consists of a human-guided agent for writing Lean specifications of code, a formal semantics of AArch64 machine code, and a team of autonomous prover agents whose proofs are accepted only if Lean’s kernel checks them against the approved specification. Applied to libsignal, our agents generated about 6.5 million lines of machine-checked Lean proof code, resting on about 26,000 lines of trusted specifications and AArch64 semantics. The proofs cover Signal’s post-quantum PQXDH handshake and Triple Ratchet, establishing forward secrecy, authentication, post-compromise security, and handshake secrecy. They are the first proofs connecting protocol-level security guarantees to the unmodified code of a widely used cryptographic protocol implementation. The results suggest that AI can make formal verification, historically too expensive for most software, practical for real-world systems. Our Lean development is available at https://google-deepmind.github.io/code-verification.

Tutorial: Introduction to Formal Verification with Lean (Part 1) - HashCloak

A tutorial Formal Verification using Lean for cryptographic engineers. Implement and prove correctness of the One-Time pad following a cryptography book.

LLMs are making formal software verification feasible at a much larger scale

Claude formally proved security properties in the compiled code of 123 open-source libraries. Along the way, it found bugs that had eluded detection for years.

Formal Verification Reference - Aura

This document describes the formal verification infrastructure that provides mathematical guarantees for Aura protocols through Quint model checking, Lean theorem proving, and Telltale session type verification.

CE Labs

Secure systems engineering, verified all the way down to the cryptography.

badge.blue — CID-First Attestation Specification

Specification for CID-first attestations on AT Protocol records. Inline and remote cryptographic signatures with replay-attack prevention.

A New AI Tool From Google DeepMind Proved the Signal Protocol Is Secure

DeepMind researchers were able to formally verify that the widely used encryption protocol works as intended. Their stretch goal? Do the same for “all the software of the world.”

Gemini JiTOR Jailbreak: Unredacted Methodology

How I taught Gemini to build its own euphemisms on the fly, bypass its safety filters, and comply with prompts it would otherwise refuse. Full methodology, now that the specific payload is patched.

Agent Client

Chat with Claude Code, Codex, Gemini CLI, and more via the Agent Client Protocol — right from your vault.

Palomar – a registry of Lean verified mathematics

In recent months there has been a proliferation of AI-generated proofs of various old and new results, some of which have been formalized in the proof assistant language Lean. However, checking tha…

Gemini network protocol specification

When Science Goes Agentic

In a couple of years, we will inspect AI-generated source code about as often as we inspect the assembly output of a compiler. Which is to say, far less often—outside of high-stakes and adversarial settings. The trajectory is clear: vibe coding is not a fad but a transition, a stepping stone. Debugging AI-generated code will shrink dramatically for a lot of everyday software—not because the code will be flawless, but because the feedback loops between generation, testing, and correction will tighten until human inspection becomes the bottleneck rather than the safeguard. In this respect, requiring the co-generation, with code, of mechanically verifiable formal attestations can also improve the process.

AIが暗号ソフトの安全性を数学的に証明する時代へ：Google DeepMind「AlphaProof Code」の衝撃

Google DeepMindが発表した「AlphaProof Code」は、Signal暗号プロトコルの機械語実装に対して主要なセキュリティ特性を数学的に証明した。検証期間を4週間に短縮した成果の裏にある、約2万6,000行の信頼基盤と厳密な前提条件の境界を読み解く。

Self-reinforcing quality / adopting verification pattern

After implementing the small-change pattern, Imprint Engineering’s next focus in improving our development loop has been implementing a verification loop for our software development. This is an increasingly common pattern, particularly popularized by poteto’s pstack, but you’ll find similar ideas emerging in other places as well, e.g. Niko Matsakis’ post on the correctness ratchet, among others. This captures some of the confusion I’ve seen in our initial rollout, and the particulars of how we are implementing the approach.