cs.CRNov 6, 2026

MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory

Authors: David H. Yang, Blake Bullwinkel, Amanda Minnich, Mohammad Mohammadi Amiri, Giorgio Severi

Organizations: Rensselaer Polytechnic Institute · Microsoft

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 long-horizon trajectories covering four domains, and supports five different memory systems. Through our evaluation, we find that all memory systems are susceptible to memory poisoning, with substantial variation in downstream effects. We further propose a memory-aware poison optimization process that increases the poisoning efficacy, highlighting differences between memory architectures. We hope that MemoryDojo will support research on understanding and mitigating agentic memory risks.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

    Jun 3, 2026Pritam Dash, Tongyu Ge, Aditi Jain +2AI Agent Security BenchmarksAgent Memory Poisoning

  2. MemForm: Benchmarking Memory Formation Poisoning in LLM Agents

    Oct 10, 2026Haowen Pan, Pengyang Shao, Yunshan Ma +4Agent Memory PoisoningPersistent Memory for Language Models

  3. Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents

    Oct 9, 2026Lei Liu, Yunji Liang, Xiaowen Zhang +4Agent Memory PoisoningBackdoor Defense in LLMs