LATIDIA · Ciberseguridad

Hacer cumplir la divulgación responsable en la IA confidencial

arXiv: 2611.05971v1Tipo de anuncio: nuevo Resumen: Los avances en la computación confidencial de CPU y GPU permiten la IA confidencial, lo que permite a los LLM procesar las solicitudes de los usuarios sin exponerlos a proveedores de servicios o operaciones de infraestructura

La noticia

arXiv:2611.05971v1 Announce Type: new Abstract: Advances in CPU and GPU confidential computing enable confidential AI, allowing LLMs to process user prompts without exposing them to service providers or infrastructure operators. However, AI agents often need to send prompt-derived information to external services, and providers may also require limited disclosure for safety monitoring and failure diagnosis. We propose CORDE, a system for confidential virtual machines (CVMs) designed to satisfy the principle of Confine or Declare: user-derived data is confined by default, but when necessary, it may leave the CVM only after being "declared." To "declare" data is to record its exact contents, recipient, and stated reason in a user-accessible, tamper-evident declaration