Conference paper · 2025 · Open access

Memory Injection Attacks on LLM Agents via Query-Only Interaction

Shen Dong, Shaochen Xu, Pengfei He, Yige Li, Jiliang Tang, Tianming Liu, Hui Liu, Zhen Xiang

neural information processing systems, 52119–52153 · Published 1 January 2025 · DOI 10.52202/085713-1554

Open PDFView at the publisherCite this paper

In brief

“Memory Injection Attacks on LLM Agents via Query-Only Interaction” is a 2025 conference paper by Shen Dong and 7 co-authors, published in neural information processing systems. OpenAlex counts 241 citations as of 19 November 2026, which puts it in the top 1% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
241
Most cited in
2026 (218)
Field-weighted impact
46.65
References
41
Authors
8

Abstract

Agents powered by large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised memory bank may easily produce harmful outputs when the past records retrieved for demonstration are malicious. In this paper, we propose a novel Memory INJection Attack, MINJA, without assuming that the attacker can directly modify the memory bank of the agent. The attacker injects malicious records into the memory bank by only interacting with the agent via queries and output observations. These malicious records are designed to elicit a sequence of malicious reasoning steps corresponding to a different target query during the agent's execution of the victim user's query. Specifically, we introduce a sequence of bridging steps to link victim queries to the malicious reasoning steps. During the memory injection, we propose an indication prompt that guides the agent to autonomously generate similar bridging steps, with a progressive shortening strategy that gradually removes the indication prompt, such that the malicious record will be easily retrieved when processing later victim queries. Our extensive experiments across diverse agents demonstrate the effectiveness of MINJA in compromising agent memory. With minimal requirements for execution, MINJA enables any user to influence agent memory, highlighting the risk.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Dong, S., Xu, S., He, P., Li, Y., Tang, J., Liu, T., Liu, H., & Xiang, Z. (2025). Memory Injection Attacks on LLM Agents via Query-Only Interaction. neural information processing systems, 52119–52153. https://doi.org/10.52202/085713-1554

MLA 9

Dong, Shen, et al. “Memory Injection Attacks on LLM Agents via Query-Only Interaction.” neural information processing systems, 2025, pp. 52119–52153. https://doi.org/10.52202/085713-1554.

Chicago

Dong, Shen, Shaochen Xu, Pengfei He, Yige Li, Jiliang Tang, Tianming Liu, Hui Liu, and Zhen Xiang. 2025. “Memory Injection Attacks on LLM Agents via Query-Only Interaction.” neural information processing systems: 52119–52153. https://doi.org/10.52202/085713-1554.

Harvard

Dong, S. et al. (2025) ‘Memory Injection Attacks on LLM Agents via Query-Only Interaction’, neural information processing systems, pp. 52119–52153. doi:10.52202/085713-1554.

IEEE

S. Dong et al., “Memory Injection Attacks on LLM Agents via Query-Only Interaction,” neural information processing systems, pp. 52119–52153, 2025, doi: 10.52202/085713-1554.

BibTeX

@inproceedings{dong2025memory,
  title     = {{Memory Injection Attacks on LLM Agents via Query-Only Interaction}},
  author    = {Dong, Shen and Xu, Shaochen and He, Pengfei and Li, Yige and Tang, Jiliang and Liu, Tianming and Liu, Hui and Xiang, Zhen},
  booktitle = {neural information processing systems},
  year      = {2025},
  pages     = {52119--52153},
  doi       = {10.52202/085713-1554},
  url       = {https://doi.org/10.52202/085713-1554}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • LLM agents
  • agent security

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Dong, S., Xu, S., He, P., Li, Y., Tang, J., Liu, T., Liu, H., & Xiang, Z. (2025). Memory Injection Attacks on LLM Agents via Query-Only Interaction. neural information processing systems, 52119–52153. https://doi.org/10.52202/085713-1554

How many times has this paper been cited?

241 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Shen Dong, Shaochen Xu, Pengfei He, Yige Li, Jiliang Tang, Tianming Liu, Hui Liu, Zhen Xiang.

What is the DOI of this paper?

10.52202/085713-1554, permanently at https://doi.org/10.52202/085713-1554. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.