DeepMind 发布 AlphaProof Code：用 Lean 验证 Signal 核心加密代码
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
DeepMind 的证明智能体给 Signal 核心加密写了三百万行 Lean 证明，等于把代码正确性变成数学定理。以前只有小团队手工做形式化验证，现在能自动化铺到真实加密系统上。做密码学、安全审计或高可靠软件的人很该看看这套工作流。
Google DeepMind 发布 AlphaProof Code，一组验证智能体为 Signal 的核心加密代码编写了约三百万行 Lean 形式化证明，实现对复杂软件的深度数学验证。
工作方式是把软件正确性命题翻译成 Lean 定理，再由智能体搜索并撰写完整证明，证明通过即代表对应代码性质在数学上成立。Signal 是全球广泛使用的端到端加密通讯协议，其核心加密逻辑此前主要依赖人工审计与传统测试，这类大规模机器生成证明覆盖属于少见的应用规模。
对密码学与高安全软件领域而言，这展示了 LLM 驱动的证明智能体在真实关键系统上的可用性，开发团队可借此把关键模块的正确性从测试保障提升到形式化证明保障。
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include AlphaProof Code, DeepMind, Lean, Signal.
Primary source verification: published directly by Google DeepMind: Blog with first-party authority.
