Google DeepMind 用 AlphaProof Code 首次从代码层面证明 Signal 协议安全性
For the first time, AI has mathematically proven @signalapp’s protocol is secure down to the code le...
AI 第一次把形式化验证做到了代码层面，被验证的还是 Signal 这种保护数十亿人消息的加密系统。做密码学、安全审计或者关心端到端加密的人应该看看，AI 定理证明正在从数学竞赛走向真实软件验证。
Google DeepMind 宣布，其 AlphaProof Code 框架首次以数学方式证明了 Signal 消息应用加密协议的安全性，验证范围深入到代码层面。
Signal 的加密系统每天保护数十亿条私人消息，是端到端加密通信的事实标准之一。此前形式化验证通常停留在协议描述层面，无法覆盖实现代码中的漏洞，AlphaProof Code 将机器学习驱动的定理证明能力延伸到了代码级验证。
这一结果意味着密码学实现中难以人工审计的部分，现在可以通过 AI 定理证明器系统性地检验。对依赖 Signal 协议的 WhatsApp 等产品和整个端到端加密生态来说，代码级安全证明提供了一种此前不存在保障强度。
For the first time, AI has mathematically proven @signalapp’s protocol is secure down to the code le...
For the first time, AI has mathematically proven @signalapp ’s protocol is secure down to the code level. Using our breakthrough AlphaProof Code framework, we verified the messaging app’s cryptographic system – which protects billions of private messages every day.📊 93 ⚡
This report is categorized under AITOP's "Industry" 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. Key entities and technical topics under continuous tracking include AlphaProof, Signal, 形式化验证, AI安全.
Source attribution: curated from Google DeepMind (@GoogleDeepMind).
