AI RESEARCH
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
arXiv CS.LG
•
ArXi:2605.03482v1 Announce Type: cross Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We formalize memory poisoning attacks on retrieval-augmented agents as a Stackelberg game with a unified evaluation framework spanning three attack classes with escalating access assumptions. Correcting an evaluation protocol inconsistency in the triggered-query specification of Chen, we show faithful evaluation increases measured attack success by $4\times$ (ASR-R: $0.25 \to 1.00.