LATIDIA · Ciberseguridad

Juzgar antes de la propagación: integridad contextual del gráfico de tareas para la privacidad multiagente

arXiv: 2610.39532v1Announce Type: new Abstract: Los sistemas LLM multiagente dependen cada vez más de la memoria persistente y la comunicación entre agentes. Estas capacidades crean riesgos de privacidad que se extienden más allá de la interacción individual

La noticia

arXiv:2610.39532v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual interactions: a release appropriate in isolation may become inappropriate when combined with information previously disclosed to a recipient or propagated to downstream agents along the planned workflow. Existing Contextual Integrity (CI) mechanisms for agentic systems typically rely on local judgments that assess each disclosure in isolation, with or without regard to the recipient's history, but do not account for how information propagates downstream. However, compliance at the current boundary does not guarantee appropriateness across the workflow. We introduce Task-Graph Contextual Integrity (TG-CI), to our knowledge