LATIDIA · Ciberseguridad

ATrust: Expansión adaptativa del límite de confianza para la seguridad de los agentes LLM

arXiv:2611.02741v1 Anuncio Tipo: nuevo Resumen: A medida que los agentes de modelos de lenguaje grandes (LLM) asumen tareas más complejas con mayor autonomía, la seguridad se ha convertido en un obstáculo importante para su implementación más amplia. A diferencia de los ataques t

La noticia

arXiv:2611.02741v1 Announce Type: new Abstract: As large language model (LLM) agents take on more complex tasks with greater autonomy, security has become a major obstacle to their broader deployment. Unlike in attacks that require complex exploitation of operating system vulnerabilities, attackers can easily hijack agents through indirect prompt injection (IPI), leading to privacy leakage, financial loss, and destructive operations. However, existing defenses often make security decisions based on limited static trusted evidence or assess observations in isolation. Such rigid trust assumptions can cause task-essential information to be unnecessarily discarded, resulting in over-defense and degraded agent functionality. To address this problem, we propose ATrust, a defense mechanism that adaptively expands the