Volver al Monitor / Back to MonitorID: ed-e1c8ba933c094a042bdb
IA & Seguridad / AI & Security[GLOBAL] • GLOBALSchneier on SecurityBruce Schneier
ANÁLISIS EDITORIAL & RESUMEN EJECUTIVO (ES)

Verificación formal del protocolo Signal mediante inteligencia artificial

Google DeepMind ha demostrado la eficacia de la IA agéntica para la verificación formal de protocolos criptográficos a gran escala al analizar Signal con AlphaProof Code. Este avance no solo valida de forma independiente la seguridad del cifrado empleado en plataformas como WhatsApp y Google Messages, sino que posiciona a las herramientas de IA como un mecanismo viable para auditar código crítico y certificar garantías matemáticas de seguridad.
STRATEGIC EDITORIAL ABSTRACT (EN)

Formal Verification of the Signal Protocol Using AI

Google DeepMind demonstrated the viability of agentic AI in cryptographic formal verification by auditing the Signal protocol using its AlphaProof Code framework. This milestone provides independent validation for encryption safeguarding billions of users across platforms like WhatsApp and Google Messages, while establishing automated AI-driven verification as a feasible approach for identifying theoretical flaws in complex security protocols.

TEXTO ORIGINAL • ORIG: [EN]

Formal Verification of the Signal Protocol Using AI

This seems like a good thing: Google Deepmind researchers used agentic AI to mathematically prove, or “formally verify,” a number of the Signal protocol’s key cryptographic guarantees­a landmark development for the widely used cryptography and AI itself. Conducted as a sort of proof-of-concept project in just four weeks, the work is significant in two ways. It serves as further independent validation of the cryptography that protects massive quantities of the world’s communications on platforms like the Signal app, Google Messages, and WhatsApp. And it demonstrates Google DeepMind’s formal verification capabilities using a new AI framework called AlphaProof Code. […] The DeepMind analysis did not find any new vulnerabilities in the portions of the Signal protocol it looked at, but when the researchers used AlphaProof Code on older versions of Signal that contain known and long-fixed vulnerabilities, it correctly identified them and showed that the protocol could not be formally verifie

Publicación Original: Schneier on SecurityLeer artículo completo en la fuente ↗