LATIDIA · Ciberseguridad

MAS-Shield: un marco de defensa para un LLM MAS seguro y eficiente

arXiv:2511.22924v3 Tipo de anuncio: replace-cross Resumen: Los sistemas multiagente (MAS)basados en el modelo de lenguaje grande (LLM) son susceptibles a ataques lingüísticos que pueden desencadenar fallos en cascada en toda la red.

La noticia

arXiv:2511.22924v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fundamental dilemma: lightweight single-auditor methods are prone to single points of failure, while robust committee-based approaches incur prohibitive computational costs in multi-turn interactions. To address this challenge, we propose \textbf{MAS-Shield}, a secure and efficient defense framework designed with a coarse-to-fine filtering pipeline. Rather than applying uniform scrutiny, MAS-Shield dynamically allocates defense resources through a three-stage protocol: (1) \textbf{Critical Agent Selection } strategically targets high-influence nodes to narrow the defense surface; (2) \textbf{Light Auditing} employs lightweight sentry models to rapidly filter the