Overview

Agent memory poisoning examines how misleading or malicious information enters an AI agent’s persistent memory and shapes behavior across later tasks or sessions. Attacks can exploit external content, memory updates, retrieval, consolidation, multimodal inputs, or sharing between agents, sometimes steering tool use long after the original exposure. Defenses include provenance tracking, source-trust limits, write-time anomaly checks, retrieval-time controls, cryptographic lineage, and selective auditing or rollback; benchmarks increasingly test persistence, downstream effects, and repair. A central challenge is distinguishing harmful content from useful but untrusted evidence: static filters can miss attacks assembled across records or activated by context, while stricter controls can block legitimate learning and adaptation.

Latest papers

CardsList

85 papers11 papers in the last four weeks, up 22% on the four weeks before. 0.1% of all new papers.

  1. On Private Knowledge Retrieval and Private Inference for secure multi-agent systems

    Nov 10, 2026Vicenç Torra, Maria Bras-AmorósPrivacy Protection for LLM AgentsMulti-Agent System Security

  2. ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems

    Nov 8, 2026Riya Bharathwaj, Akshara Prabhakar, Roshan Ram +4AI Agent Safety BenchmarksMulti-Agent LLM Systems

  3. When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization

    Nov 7, 2026Minhua Lin, Zongyu Wu, Hanqing Lu +4LLM Backdoor AttacksBackdoor Attacks

  4. MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory

    Nov 6, 2026David H. Yang, Blake Bullwinkel, Amanda Minnich +2Agent Memory PoisoningMemory Agent Benchmarks

  5. MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents

    Nov 1, 2026Zhihua Wang, Yunhao Feng, Yifeng Gao +4Prompt Injection AttacksPrompt Injection Attacks on AI Agents

  6. Accept Changes, Reject Attacks: Robust Memory Management for LLM Agents

    Oct 29, 2026Runze Zhao, Dongruo Zhou, Sumit Kumar Jha +2Memory Management for LLM AgentsAgent Memory Poisoning

  7. Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction

    Oct 28, 2026Haoran Bu, Yiting Shen, Litian Zhang +2AI Agent SecurityLLM Agent Safety

  8. After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

    Oct 20, 2026Zhiyue Xu, Xukai Wang, Zhiyuan Huang +3Adversarial Attacks on LLMsPrompt Injection Attacks on AI Agents

  9. ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents

    Oct 20, 2026Jinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique +4AI Agent SecurityMemory Management for LLM Agents

  10. AutoRedClaw: Automated Red-Teaming for Claw-Style Agents

    Oct 19, 2026Hao Li, Tongyan Hu, Weidi Luo +8AI Agent SecurityAutomated Red Teaming

  11. SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval

    Oct 16, 2026Haoming Li, Dingyi Kang, Xu Hu +8Persistent Memory for Language ModelsAgent Memory Poisoning

  12. MemForm: Benchmarking Memory Formation Poisoning in LLM Agents

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

  13. 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

  14. SkillPoison: Progressive Skill Poisoning via Successful Experiences

    Oct 6, 2026Lizhi Zhang, Xin He, Dianxuan Fu +5Adversarial AttacksLLM Agent Safety

  15. Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough

    Oct 2, 2026Debeshee Das, Jacqueline Tay, Bruce Tsai +2LLM Agent SafetyAI Alignment

  16. VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents

    Sep 29, 2026Yurong Hao, Wen Zhou, Guowei Guan +3Adversarial AttacksAgent Memory Poisoning

  17. Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents

    Sep 28, 2026Sidharth Pulipaka, Ansh Sharma, Stanislau Hlebik +4AI Agent SecurityAgent Memory Poisoning

  18. From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents

    Sep 28, 2026Mingxi Zou, Langzhang Liang, Zhuo Wang +3Adversarial AttacksAgent Memory Poisoning

  19. A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory

    Sep 25, 2026Xiaoyang Li, Yiqi Wang, Chencheng Zhu +6Memory Agent BenchmarksAgent Memory Management

  20. When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

    Sep 12, 2026Shuhuai Huang, Jingfeng Zhang, Hong JiaLLM Agent SecurityAgent Memory Poisoning

  21. InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

    Aug 24, 2026Hanling Tian, Gengyu Zhang, Zeyang Sha +5LLM Agent MemoryPrompt Injection Attacks on AI Agents

  22. MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Content

    Aug 22, 2026Minjae Seo, Wonwoo Choi, Geonwoo Han +7AI Agent SecurityAgent Memory Poisoning

  23. GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities

    Aug 18, 2026Haoran Bu, Zejian Chen, Litian Zhang +1AI Agent SecurityMulti-Agent LLM Systems