AI · Article
DeepMind's AlphaProof Code Uses AI to Machine-Verify Signal's Encryption Code
사이언스모니터 ·

At a glance
Google DeepMind unveiled AlphaProof Code, an AI agent system that mathematically proves software works as specified. The company says it used the system to verify the core code of the Signal messenger's encryption protocol in about four weeks.
Key points
- Formal verification, a method of proving with mathematics that a program follows its specification, was handled largely by AI.
- Human experts review every formal specification and re-check about 1% of the code the agent flagged.
- Proofs are checked in Lean, a tool that lets a computer confirm each proof step, so wrong proofs get filtered out.
- When two previously fixed bugs were put back into a copy of the code, the system produced a proof that the buggy version was unsafe.
Why it matters
Bugs in encryption code for messengers like Signal can have wide impact. If this approach spreads, verification of security-critical code could become more common. However, all figures come from DeepMind's own announcement.
Original source
구글 딥마인드 ‘알파프루프 코드’, 시그널 암호 프로토콜 구현을 AI로 기계 검증…사람 재검토는 약 1%
사이언스모니터 · Nov 11, 10:18 KST
Read on 사이언스모니터 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 사이언스모니터.
Other coverage
- WIRED · A New AI Tool From Google DeepMind Proved the Signal Protocol Is Secure
- Ars Technica · Signal’s encryption just passed an AI-powered mathematical checkup
- Google DeepMind blog · Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
- 뉴스N연합 · 구글 딥마인드 '알파프루프 코드', 시그널 암호화 프로토콜 기계어 수준 정식 검증 성공…보안 인증 시장 재편 압력 가시화
- Unite.AI · Google DeepMind, AI 에이전트로 Signal의 핵심 기계어 코드 검증
- GeekNews · AlphaProof Code - Signal 암호화 구현을 기계어 수준에서 형식 검증
- knpp.co.kr · 구글 딥마인드 '알파프루프 코드', 시그널 암호화 프로토콜 기계어 수준 정식 검증 성공…보안 인증 시장 재편 압력 가시화
- VOI.ID · 구글 딥마인드, 신호 및 WhatsApp 암호화 프로토콜의 보안을 입증
Google DeepMind · Ranking and more news
More from this field
- Amazon CloudWatch Omni Adds Microsoft Azure Logs, Metrics, and Traces Support
Amazon CloudWatch Omni can now collect Azure resource logs, Azure Monitor platform metrics, virtual network flow logs, and Application Insights traces. Teams running workloads on both AWS and Azure can view all of this telemetry in one place, without separate tools or custom pipelines.
AWS What's New · Nov 21, 10:10 KST - AWS Quick Adds Chat-Built Flows, Updated Web App, and Teamwork Among Agents
AWS Quick added updates that let a team turn one person's work routine into a shared, repeatable process. Flows can now be built and changed entirely in chat, and they can run from the web, desktop, or mobile app. Agents working together can also give more complete answers.
Amazon AWS Machine Learning blog · Nov 21, 10:06 KST - Oracle Says It Has Secured Funding for OpenAI Infrastructure Deal
Oracle said it has secured all the funding needed for its infrastructure deal with OpenAI. It described itself as the first giant cloud provider to fully finish raising money for this investment cycle. The announcement came after Oracle said in early November that it had completed its final fundraising.
Unite.AI · Nov 21, 09:47 KST - Claude Claims Proof of 167-Year-Old Riemann Hypothesis, Pending Expert Review
Anthropic researcher Levent Alpoge says he and Claude found a proof of the Riemann Hypothesis, a famous unsolved math problem. The claim is not yet verified by the academic community.
싱글리스트 · Nov 21, 09:22 KST