LATIDIA · Ciberseguridad

SAFE-Mem: Memoria Agénica Segura con Autoridad Fina y Recuperación Consciente de la Gobernanza

arXiv: 2610.22959v1Tipo de anuncio: nuevo Resumen: los agentes del modelo de lenguaje grande (LLM) dependen cada vez más de la memoria persistente para respaldar el razonamiento a largo plazo y las interacciones personalizadas. Sin embargo, la información recopilada de e

La noticia

arXiv:2610.22959v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized interactions. However, information collected from external sources can introduce security risks when untrusted claims (i.e., atomic statements) are later treated as authorized preferences, policies, or permissions. Existing defenses typically rely on content-based filtering or coarse-grained provenance tracking, which either fail to prevent unauthorized memory use or block legitimate information, sacrificing memory utility. To address these limitations, we propose SAFE-Mem, a fine-grained memory governance framework that improves security while preserving legitimate memory use. First, SAFE-Mem annotates each claim with three governance labels (i.e., kind, authority, and scope) to capture its