LATIDIA · Ciberseguridad

Ilusión: salvaguardando la confidencialidad de la topología en sistemas multiagente LLM mediante ofuscación que preserva el comportamiento.

arXiv:2611.00923v1 Anuncio Tipo: nuevo Resumen: La topología de comunicación de los sistemas multiagente de modelos de lenguaje grandes (LLM-MAS) rige cómo se propaga la información entre los agentes y codifica el conocimiento crítico del dominio y

La noticia

arXiv:2611.00923v1 Announce Type: new Abstract: The communication topology of Large Language Model Multi-Agent Systems (LLM-MASs) governs how information propagates among agents and encodes critical domain knowledge and expert workflow design. It is valuable intellectual property and plays a decisive role in system utility and safety, yet remains vulnerable to inference attacks that stealthily reconstruct it from agent outputs. Existing defenses detect or mitigate such attacks but do not proactively conceal the topology itself. We propose \textit{Illusion}, a proactive topology obfuscation defense for LLM-MAS. \textit{Illusion} injects fake edges and fake messages to present attackers with a deceptive topology, while selecting low-impact candidates that preserve output-distribution equivalence and task-accuracy non-inferiority. The resulting