今天,我们分享了一项在软件安全领域长期被视为重大挑战的里程碑式成果:Google DeepMind 的研究人员引导 AI 智能体对 Signal 协议底层实际代码的关键安全属性进行了数学证明。Signal 是保护 Signal 和 Google Messages 等应用中数十亿次私密对话的技术。
我们的工作首次利用 AI 以这种深度对广泛部署的加密协议进行了形式化验证。这也是首次通过任何方法(无论是否使用 AI)对像这样广泛部署的协议的实现进行形式化验证。
接下来,智能体会审计这些证明,并标出需要人类再次审视的区域——仅占整个代码库的百分之一,极大地节省了时间。由于 Lean 会自动检查其余部分,我们的专家可以将精力集中在最需要人类判断力的地方。
但大多数协议验证仅停留在设计层面。我们的智能体更进一步,证明了编译后的代码能够满足关键的安全属性——例如,在设备暂时被攻破前后保持消息受保护——直至设备运行的确切代码。由于现实世界中的漏洞往往隐藏在设计与实际实现之间的差距中,弥合这一差距使得这些证明变得极其复杂。
即便面对如此高的复杂度,我们的验证过程仅用了四周时间——而历史上这需要专家团队花费数年——这证明了 Signal 的核心加密代码确实提供了我们专家所指定的安全保护。
为了确认 AlphaProof Code 能够区分正确代码和有缺陷的代码,我们将两个真实存在、此前已修复的漏洞重新引入到一个隔离版本的 Signal 代码中。在这两种情况下,系统都生成了一个由机器检查的证明,表明有缺陷的版本是不安全的。
虽然之前的形式化验证工作必然聚焦于较小的范围,但这种新方法实现了显著的扩展。传统上,验证生产代码是否严格匹配其加密设计需要大量人工努力,因此利用 AI 智能体自动将实时代码转换为有效的 Lean 定理是一个巨大的突破。随着基于 AI 的安全威胁日益增长,对核心 Signal 协议进行严格的自动化定理证明验证,使我们对其代码兑现隐私保证的信心更加增强。
本研究由 Swarat Chaudhuri、Andrew Ferraiuolo、Anton Kovsharov、Tej Chajed、Sam Schlesinger、Karn Seth、Jonathan Katz、Charles Sutton 和 Pushmeet Kohli 开发。
我们要感谢 Eric Wieser 在开源代码方面提供的帮助,Owen Jones 在项目管理工作上的支持,以及 Martín Abadi、Christopher Henson、Katerina Hristova、Henryk Michalewski、Jonathan Protzenko 和 George Tsoukalas 提供的有益讨论。我们要感谢 Signal 的 Rolfe Schmidt、Michael Rosenberg 和 Ehren Kret 对我们方法论提出的反馈。我们还要感谢 Tulsee Doshi、Four Flynn、Kate Olszewska、Alicia Huang、Andy Liu、Benoit Schillings、Raluca Ada Popa、Melvin Johnson、Koray Kavukcuoglu、Demis Hassabis 和 Sundar Pichai 对该项目的支持。
查看原文
November 10, 2026 Research
Pushmeet Kohli and Swarat Chaudhuri
How Google DeepMind researchers built a new agentic framework that formally verified the code of Signal’s cryptographic protocol — long considered to be a grand security challenge
Today, we’re sharing a milestone in software security long considered to be a grand challenge: Google DeepMind researchers guided AI agents to mathematically prove key security properties of the actual code underlying the Signal protocol, the technology that protects billions of private conversations in apps like Signal and Google Messages.
This breakthrough discovery was made using AlphaProof Code, a novel agentic framework for formal verification at unprecedented depth that combines human expertise with AI agents. Formal verification—mathematically proving code runs correctly without flaws—is the highest standard of security assurance; however, it is difficult and often labor-intensive.
Our work marks the first time AI has been used to formally verify a widely deployed cryptographic protocol at this depth. It's also the first time the implementation of a widely deployed protocol like this has been formally verified by any method, with or without AI.
How we verified Signal
AlphaProof Code is a multi-LLM agentic framework that splits the work of formal verification the way a research team would: human experts work with AI to decide what to prove, and a group of AI agents does it.
First, our researchers collaborated with a mix of models to translate Signal’s security goals into formal mathematical specifications, with human experts reviewing every one. From there, agents powered by Gemini Carbon did the proofs, generating over six million lines of Lean, a computer language that mathematically proves the accuracy of code.
Next, the agents audited the proof and highlighted areas that needed a second look by a human – just one percent of the codebase, a massive time savings. Because Lean automatically checks the rest, our experts could focus their review where human judgment matters most.
Cryptographic protocols underpin nearly all digital communication, from online banking to web browsing, and a single flaw can expose millions of people at once. That's why experts have spent decades formally analyzing them.
But most protocol verification stops at the design level. Our agents went further, proving that the compiled code fulfills the key security properties – such as keeping messages protected before and after a device is temporarily compromised – down to the exact code running on devices. Because real-world vulnerabilities often hide in the gap between design and implementation, bridging this gap makes these proofs vastly more complex.
Even at this complexity, our verification process took just four weeks – a task that historically takes expert teams years – proving that Signal's core cryptographic code delivers the security protections our experts specified.
To confirm that AlphaProof Code can tell correct code from buggy code, we reintroduced two real, previously fixed bugs into an isolated version of Signal's code. In both cases, the system produced a machine-checked proof that the buggy version was insecure.
In AlphaProof Code, AI agents help users write a specification, then autonomously prove that the implementation meets it. Every proof is checked by Lean to verify the agents' work.
While prior formal verification work has necessarily focused on smaller scopes, this new approach enables a significant expansion. Traditionally, verifying that production code strictly matches its cryptographic design required extensive manual effort, making the use of AI agents to automatically translate live code into valid Lean theorems a great breakthrough. As AI-driven security threats grow, having the core Signal protocol rigorously verified with automated theorem proving gives us even greater confidence that our code delivers on its privacy guarantees.
The future of security
Achieving this long-standing challenge demonstrates how AI can bring elite security assurance to businesses, governments, and critical infrastructure, helping defend against agent-driven cyber threats.
Verifying Signal's core cryptography lays the groundwork to secure other vital systems, from medical device firmware to power grid software.
Scaling these techniques requires continued research. Paired with automated defense agents like CodeMender, formal verification can help counter the speed and scale of modern cyber threats to create software with mathematical proof that its protections work.
We are open-sourcing our formal verification artifacts for community use. Read the technical paper below.
Acknowledgements
This research was developed by Swarat Chaudhuri, Andrew Ferraiuolo, Anton Kovsharov, Tej Chajed, Sam Schlesinger, Karn Seth, Jonathan Katz, Charles Sutton, and Pushmeet Kohli.
We thank Eric Wieser for help with open-sourcing our code, Owen Jones for program management support, and Martín Abadi, Christopher Henson, Katerina Hristova, Henryk Michalewski, Jonathan Protzenko and George Tsoukalas for helpful discussions. We thank Signal's Rolfe Schmidt, Michael Rosenberg, and Ehren Kret for their feedback on our methodology. We also thank Tulsee Doshi, Four Flynn, Kate Olszewska, Alicia Huang, Andy Liu, Benoit Schillings, Raluca Ada Popa, Melvin Johnson, Koray Kavukcuoglu, Demis Hassabis, and Sundar Pichai for their support of the project.