Conference paper · 2025 · Open access
Unveiling Privacy Risks in LLM Agent Memory
Proceedings of the conference - Association for Computational Linguistics. Meeting, 25241–25260 · Published 1 January 2025 · DOI 10.18653/v1/2025.acl-long.1227
In brief
“Unveiling Privacy Risks in LLM Agent Memory” is a 2025 conference paper by Bo Wang and 6 co-authors, published in Proceedings of the conference - Association for Computational Linguistics. Meeting. OpenAlex counts 175 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 Proceedings of the conference - Association for Computational Linguistics. Meeting.
- Citations
- 175
- Most cited in
- 2026 (143)
- Field-weighted impact
- 36.34
- References
- 36
- Authors
- 7
Abstract
Large Language Model (LLM) agents have become increasingly prevalent across various realworld applications.They enhance decisionmaking by storing private user-agent interactions in the memory module for demonstrations, introducing new privacy risks for LLM agents.In this work, we systematically investigate the vulnerability of LLM agents to our proposed Memory EXTRaction Attack (MEXTRA) under a black-box setting.To extract private information from memory, we propose an effective attacking prompt design and an automated prompt generation method based on different levels of knowledge about the LLM agent.Experiments on two representative agents demonstrate the effectiveness of MEXTRA.Moreover, we explore key factors influencing memory leakage from both the agent designer's and the attacker's perspectives.Our findings highlight the urgent need for effective memory safeguards in LLM agent design and deployment.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, B., He, W., Zeng, S., Xiang, Z. J., Xing, Y., Tang, J., & He, P. (2025). Unveiling Privacy Risks in LLM Agent Memory. Proceedings of the conference - Association for Computational Linguistics. Meeting, 25241–25260. https://doi.org/10.18653/v1/2025.acl-long.1227
MLA 9
Wang, Bo, et al. “Unveiling Privacy Risks in LLM Agent Memory.” Proceedings of the conference - Association for Computational Linguistics. Meeting, 2025, pp. 25241–25260. https://doi.org/10.18653/v1/2025.acl-long.1227.
Chicago
Wang, Bo, Weiyi He, Shenglai Zeng, Zhen James Xiang, Yue Xing, Jiliang Tang, and Pengfei He. 2025. “Unveiling Privacy Risks in LLM Agent Memory.” Proceedings of the conference - Association for Computational Linguistics. Meeting: 25241–25260. https://doi.org/10.18653/v1/2025.acl-long.1227.
Harvard
Wang, B. et al. (2025) ‘Unveiling Privacy Risks in LLM Agent Memory’, Proceedings of the conference - Association for Computational Linguistics. Meeting, pp. 25241–25260. doi:10.18653/v1/2025.acl-long.1227.
IEEE
B. Wang et al., “Unveiling Privacy Risks in LLM Agent Memory,” Proceedings of the conference - Association for Computational Linguistics. Meeting, pp. 25241–25260, 2025, doi: 10.18653/v1/2025.acl-long.1227.
BibTeX
@inproceedings{wang2025unveiling,
title = {{Unveiling Privacy Risks in LLM Agent Memory}},
author = {Wang, Bo and He, Weiyi and Zeng, Shenglai and Xiang, Zhen James and Xing, Yue and Tang, Jiliang and He, Pengfei},
booktitle = {Proceedings of the conference - Association for Computational Linguistics. Meeting},
year = {2025},
pages = {25241--25260},
doi = {10.18653/v1/2025.acl-long.1227},
url = {https://doi.org/10.18653/v1/2025.acl-long.1227}
}
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
- memory leakage
- privacy attacks
- black-box attacks
- prompt engineering
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wang, B., He, W., Zeng, S., Xiang, Z. J., Xing, Y., Tang, J., & He, P. (2025). Unveiling Privacy Risks in LLM Agent Memory. Proceedings of the conference - Association for Computational Linguistics. Meeting, 25241–25260. https://doi.org/10.18653/v1/2025.acl-long.1227
How many times has this paper been cited?
175 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 Proceedings of the conference - Association for Computational Linguistics. Meeting: sign in and open the PDF from this page.
Who wrote this paper?
Bo Wang, Weiyi He, Shenglai Zeng, Zhen James Xiang, Yue Xing, Jiliang Tang, Pengfei He.
What is the DOI of this paper?
10.18653/v1/2025.acl-long.1227, permanently at https://doi.org/10.18653/v1/2025.acl-long.1227. 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.