phenomenon · first seen 9 Oct 2026
memory poisoning attack
Also: memory poisoning
Attack that injects malicious content into an agent's persistent memory to corrupt its later behavior.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM AgentsPapers · 9 Oct 2026 · Lei Liu, Yunji Liang, Xiaowen Zhang, Jingqi Liu, Qi Li, Bin Guo, Zhiwen Yu
- MemForm: Benchmarking Memory Formation Poisoning in LLM AgentsPapers · 10 Oct 2026 · Haowen Pan, Pengyang Shao, Yunshan Ma, Yanzheng Jin, Naixin Zhai, Xiang Wang, Xu…
- GRAD: Graph-Structured Antibody Defense for LLM AgentsPapers · 16 Oct 2026 · Tianqi Song, Jiawei Du, Xuemei Jia, Zheng Wang
- SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware RetrievalPapers · 16 Oct 2026 · Haoming Li, Dingyi Kang, Xu Hu, Jinxin Yang, Zhu Xu, Chenru Wang, Yi Ge, Miao Yi…
- AutoRedClaw: Automated Red-Teaming for Claw-Style AgentsPapers · 19 Oct 2026 · Hao Li, Tongyan Hu, Weidi Luo, Shanghao Shi, Xiaogeng Liu, Aiden Suh, Yulong Cao…
- Is it my preference? Role Grounding Attack against Agent's Memory via Social InteractionPapers · 28 Oct 2026 · Haoran Bu, Yiting Shen, Litian Zhang, Ruihan Hu, Xi Zhang
Latest sources
- On Private Knowledge Retrieval and Private Inference for secure multi-agent systemsPapers · 10 Nov 2026 · Vicenç Torra, Maria Bras-Amorós
- MemoryDojo: Benchmarking Poisoning Through LLM Agent MemoryPapers · 6 Nov 2026 · David H. Yang, Blake Bullwinkel, Amanda Minnich, Mohammad Mohammadi Amiri, Giorg…
- Accept Changes, Reject Attacks: Robust Memory Management for LLM AgentsPapers · 29 Oct 2026 · Runze Zhao, Dongruo Zhou, Sumit Kumar Jha, Nathaniel D. Bastian, Ankit Shah
- Is it my preference? Role Grounding Attack against Agent's Memory via Social InteractionPapers · 28 Oct 2026 · Haoran Bu, Yiting Shen, Litian Zhang, Ruihan Hu, Xi Zhang
- AutoRedClaw: Automated Red-Teaming for Claw-Style AgentsPapers · 19 Oct 2026 · Hao Li, Tongyan Hu, Weidi Luo, Shanghao Shi, Xiaogeng Liu, Aiden Suh, Yulong Cao…
- SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware RetrievalPapers · 16 Oct 2026 · Haoming Li, Dingyi Kang, Xu Hu, Jinxin Yang, Zhu Xu, Chenru Wang, Yi Ge, Miao Yi…
- GRAD: Graph-Structured Antibody Defense for LLM AgentsPapers · 16 Oct 2026 · Tianqi Song, Jiawei Du, Xuemei Jia, Zheng Wang
- MemForm: Benchmarking Memory Formation Poisoning in LLM AgentsPapers · 10 Oct 2026 · Haowen Pan, Pengyang Shao, Yunshan Ma, Yanzheng Jin, Naixin Zhai, Xiang Wang, Xu…
- Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM AgentsPapers · 9 Oct 2026 · Lei Liu, Yunji Liang, Xiaowen Zhang, Jingqi Liu, Qi Li, Bin Guo, Zhiwen Yu