Author name: Ishrith Gowda (University of California, Berkeley)

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents

Ishrith Gowda (University of California, Berkeley) / May 8, 2026

arXiv:2605.03482v2 Announce Type: replace-cross
Abstract: Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We formalize memory poisoning attacks on retrieva…

cs.AI, cs.CR, cs.LG

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents

Ishrith Gowda (University of California, Berkeley) / May 6, 2026

arXiv:2605.03482v1 Announce Type: cross
Abstract: 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-augmen…