AI · Article
Google DeepMind Uses AI Agents to Mathematically Verify Signal's Core Code
Unite.AI ·

At a glance
Google DeepMind used a team of AI agents to prove that the core code of the messaging app Signal keeps its promised security properties. Five researchers finished the work in four weeks, and they published the proofs and verification process for outside review.
Key points
- The AI agents produced about 6.5 million lines of machine-checked proof code.
- Humans chose the security properties to verify, reviewed the specifications, and gave final approval.
- It is described as the first protocol-level security proof for unmodified code of a widely deployed cryptographic library.
- Group messaging, key generation, and the whole app were not covered by this verification.
Why it matters
It shows AI could help verify the reliability of complex security code. However, the results still depend on specifications that humans reviewed.
Original source
Google DeepMind, AI 에이전트로 Signal의 핵심 기계어 코드 검증
Unite.AI · Nov 10, 21:37 KST
Read on Unite.AI ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Unite.AI.
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
- 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
- AI 매터스 · 구글 딥마인드 ‘알파프루프 코드’, 시그널 암호 코드 4주 만에 검증
Google DeepMind · Ranking and more news
More from this field
- Meta Rethinks 2030 Net-Zero Goal as AI Data Center Emissions Hit Record High
Meta's 2026 sustainability report said the company is re-evaluating its 2030 net-zero goal. Its emissions rose about 40 percent from 2024 to 2025, the largest jump among the big US tech companies.
Ars Technica · Nov 21, 06:47 KST - Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Walter Writes AI Tool Rewrites AI Text to Sound More Human, Ad Test Shows
This short video is a sponsored ad for Walter Writes AI, a tool that rewrites AI-generated text so it reads more like a person wrote it. The creator says they ran a paragraph through its detector, rewrote the flagged parts, and compared the scores before and after.
TheAIGRID · Nov 21, 06:15 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST