MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents

Abstract

Memory-augmented LLM agents rely on rich context for long-horizon reasoning and acting, yet their memory modules expose a persistent attack surface for malicious records, making the study of memory poisoning threats imperative. However, existing query-only attacks often fail to remain effective in two realistic and prevalent settings: large-scale benign memory pools and active input auditing. Consequently, current approaches fall short when facing the dual challenges of high retrieval competitiv

Categories

Framework mappings

Suggested from the entry's categories.

@misc{chen2026mafia,
  title = {{MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents}},
  author = {Jiaming Chen and Yisen Gao and Yanping Li and Zifan Liu and Yumeng Zhang and Jun Zhang},
  year = {2026},
  month = aug,
  eprint = {2608.03844},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.03844}
}