LATIDIA · Ciberseguridad

La seguridad del agente es un problema de sistemas

arXiv:2605.18991v3 Tipo de anuncio: reemplazar Resumen: Tomamos la posición de que la seguridad del agente debe abordarse como un problema de sistemas: el modelo de IA que alimenta al agente debe tratarse como un componente no confiable y securit

La noticia

arXiv:2605.18991v3 Announce Type: replace Abstract: We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness (the dominant viewpoint in the community) are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain. Based on our experience as cybersecurity researchers in operating systems, networks, formal methods, and adversarial machine learning, we articulate a set of core principles, grounded in decades of systems security research, that provide a foundation for