LATIDIA · Ciberseguridad

ESPEJO: Integridad de quórum multitrayecto para comunicación multiagente LLM

arXiv:2610.02349v1 Anuncio Tipo: nuevo Resumen: La comunicación entre agentes es fundamental para los sistemas multiagente de modelos de lenguaje grandes (LLM-MAS), pero introduce una vulnerabilidad poco explorada: el agente en el medio (AiTM)

La noticia

arXiv:2610.02349v1 Announce Type: new Abstract: Inter-agent communication is central to Large Language Model Multi-Agent Systems (LLM-MAS), but it introduces an underexplored vulnerability: Agent-in-the-Middle (AiTM) attacks that manipulate messages in transit without compromising the agents themselves. Prior work reports Attack Success Rates (ASR) approaching 100% on structured tasks. Existing defenses rely on semantic validation, which requires additional inference and can block benign outputs, or on transport-layer encryption, which does not help when an intermediary legitimately terminates TLS. We present MIRROR, a communication-layer integrity primitive that replicates a single canonicalized payload across k logical routes and accepts a message only when a strict majority of routes report the same digest. MIRROR uses