LATIDIA · Ciberseguridad

MemoryDojo: Evaluación comparativa del envenenamiento a través de la memoria del agente LLM

arXiv: 2611.09721v1Tipo de anuncio: nuevo Resumen: los agentes de LLM se benefician del uso de sistemas de memoria para mejorar el rendimiento en tareas multisesión de largo horizonte. Sin embargo, la memoria introduce una superficie de ataque crítica. Malicioso en

La noticia

arXiv:2611.09721v1 Announce Type: new Abstract: LLM agents benefit from using memory systems to improve performance on long-horizon, multi-session tasks. However, memory introduces a critical attack surface. Malicious instructions encountered in one session may be stored and propagated through memory before being retrieved and acted upon in later sessions. Because memory systems differ in how they process and retrieve information, the downstream effects of poisoning can vary significantly across systems. To quantify the effects of poisoning across different memory architectures, we introduce MemoryDojo, a benchmark for tracing the lifecycle of poisoned information through agent memory and measuring its influence on subsequent agent behavior. MemoryDojo is easily extensible, consists of 155 multi-session