LATIDIA · Ciberseguridad

Gobernanza de la memoria consciente del linaje: un marco dependiente de la derivación para el control de acceso a nivel de columna de preservación de la privacidad en agentes de IA empresariales

arXiv: 2610.07258v1Tipo de anuncio: nuevo Resumen: los agentes de IA empresarial que comparten un almacén de memoria enfrentan dos riesgos no abordados: los datos confidenciales pueden filtrarse a través de resultados legítimamente calculados que el solicitante no pudo derivar, y

La noticia

arXiv:2610.07258v1 Announce Type: new Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently compute a same-named key performance indicator (KPI) through conflicting logic. Existing agent-memory systems (e.g., MemGPT, Zep, A-MEM) gate retrieval by content, ownership, and role, not derivation, missing a cached insight that embeds a forbidden column. We introduce the Analytical Memory Unit (AMU), a memory schema that attaches a full derivation (lineage) graph to every cached result, gated by a retrieval policy that serves a hit only when the requester is authorised for every column touched. Provided