Back to AI News
arxiv

MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory

MemoryDojo is a benchmark for tracing how poisoned information propagates through LLM agent memory systems across sessions and measuring its influence on later agent behavior. It comprises 155 multi-session long-horizon trajectories spanning four domains and supports five different memory systems. The authors report that all evaluated memory systems are susceptible to memory poisoning, with substantial variation in downstream effects across architectures. They also propose a memory-aware poison optimization process that increases poisoning efficacy, highlighting differences between memory architectures.

AI Brief

It gives agent builders a concrete benchmark and early evidence that memory architectures differ materially in how poisoned content propagates, which matters for designing safer long-horizon agents.

arXiv:2611.09721v1 Announce Type: cross 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.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!