LATIDIA · Ciberseguridad

No hay una arquitectura única para todos: una evaluación interambiental de los agentes jerárquicos del equipo rojo

arXiv: 2610.00557v1 Tipo de anuncio: nuevo Resumen: Los agentes autónomos del equipo rojo ponen a prueba cada vez más las defensas cibernéticas habilitadas por IA mediante la planificación de estrategias y la ejecución de ataques de múltiples etapas. Aprendizaje por refuerzo (RL) y gran l

La noticia

arXiv:2610.00557v1 Announce Type: new Abstract: Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning (RL) and large language models (LLMs) offer complementary mechanisms for the planning and execution such agents require, and prior work has combined them in hybrid hierarchies. Yet a given architecture is typically developed and evaluated within a single environment, leaving open whether an observed advantage reflects a generally stronger decision mechanism or merely alignment with a particular setting. We address this gap with a controlled cross-environment comparison of two homogeneous hierarchical red team architectures: an RL planner with an RL executor (RL+RL) and an LLM planner with