LATIDIA · Ciberseguridad

RACIÓN: Hacia un control cuantitativo del acceso basado en el riesgo para los agentes de IA

arXiv: 2610.24311v1Tipo de anuncio: nuevo Resumen: los agentes de IA interactúan cada vez más con entornos externos para completar tareas complejas del usuario. Estas interacciones pueden conducir a un comportamiento inesperado y exponer a los agentes a la seguridad

La noticia

arXiv:2610.24311v1 Announce Type: new Abstract: AI agents increasingly interact with external environments to complete complex user tasks. These interactions can lead to unexpected behavior and expose agents to security threats such as indirect prompt injection. Current agent security systems largely protect agents by restricting their actions, which can result in a substantial security-utility trade-off for complex, open-ended tasks. To address this, we propose a quantitative risk-based approach to access control for AI agents that regulates measurable risks accumulated during task execution. As a concrete realization of this approach, we introduce RATION, a security framework that tracks measurable risks associated with agent actions and enforces quantitative constraints throughout execution. RATION first