paperSeptember 2026Unreviewed

Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM Agents

Chuanchao Zang, Jianing Wang, Wenyu Chen, Xiangtao Meng, Li Wang, Xinyu Gao, Zheng Li, Shanqing Guo

Abstract

Long-term memory can turn untrusted external content into persistent influence over an LLM agent's future decisions, creating the threat of indirect memory poisoning. A successful attack must survive a multi-stage pipeline comprising memory writing, retrieval, and utilization. Existing attacks largely rely on intra-stage optimization, optimizing individual stages in isolation while overlooking inter-stage coupling. Specifically, these stages impose different requirements on the same poisoning co

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

OWASP Top 10 for Agentic Applications

ASI06Memory & Context Poisoning

MITRE ATLAS

AML.T0020Poison Training Data
AML.T0080AI Agent Context Poisoning

Suggested from the entry's categories.

Cite

@misc{zang2026transferable,
  title = {{Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM Agents}},
  author = {Chuanchao Zang and Jianing Wang and Wenyu Chen and Xiangtao Meng and Li Wang and Xinyu Gao and Zheng Li and Shanqing Guo},
  year = {2026},
  month = sep,
  eprint = {2609.00523},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.00523}
}