LATIDIA · Ciberseguridad

Protección basada en la intención para agentes de IA

arXiv:2611.16122v1 Tipo de anuncio: nuevo Resumen: Los agentes de IA acceden cada vez más a los datos de las empresas, recurren a herramientas potentes y actúan con una supervisión humana limitada. Las defensas de seguridad existentes detectan principalmente la inyección de «prompts», ha

La noticia

arXiv:2611.16122v1 Announce Type: new Abstract: AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine whether an agent remains faithful to the purpose for which it was deployed. An action may contain no attack pattern and stay within granted permissions while still violating the agent's role, organizational constraints, or purpose. We introduce Intent- Aware Security, a framework that treats trusted agent intent as a first-class security object. We define Intent Preservation and Intent Drift, and operationalize them through an Intent Profile: an agent-specific representation extracted from organizational, role, and