Preprint · 2025 · Open access
Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
arXiv (Cornell University) · Published 8 October 2025 · DOI 10.48550/arxiv.2510.07176
In brief
“Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions” is a 2025 preprint by Yixiang Zhang and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 16 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 16
- Most cited in
- 2026 (15)
- Authors
- 7
Abstract
Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted traffic exchanged between users and LLM agents. By analyzing traffic patterns associated with agent workflows and tool invocations, adversaries can infer agent activities, distinguish specific agents, and even profile sensitive user attributes. To highlight this risk, we develop AgentPrint, which achieves an F1-score of 0.866 in agent identification and attains 73.9% and 69.1% top-3 accuracy in user attribute inference for simulated- and real-user settings, respectively. These results uncover an overlooked risk: the very interactivity that empowers LLM agents also exposes user privacy, underscoring the urgent need for technical countermeasures alongside regulatory and policy safeguards.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhang, Y., Deng, X., Zhongyi, G., Chen, Y., Xu, K., Li, Q., & Wu, J. (2025). Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.07176
MLA 9
Zhang, Yixiang, et al. “Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2510.07176.
Chicago
Zhang, Yixiang, Xinhao Deng, Gu, Zhongyi, Yihao Chen, Ke Xu, Qi Li, and Jianping Wu. 2025. “Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.07176.
Harvard
Zhang, Y. et al. (2025) ‘Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions’, arXiv (Cornell University). doi:10.48550/arxiv.2510.07176.
IEEE
Y. Zhang et al., “Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2510.07176.
BibTeX
@misc{zhang2025exposing,
title = {{Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions}},
author = {Zhang, Yixiang and Deng, Xinhao and Zhongyi, Gu, and Chen, Yihao and Xu, Ke and Li, Qi and Wu, Jianping},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2510.07176},
url = {https://doi.org/10.48550/arxiv.2510.07176}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
- LLM agents
- user privacy
- traffic fingerprinting
- encrypted traffic analysis
- agent identification
- tool invocation
- privacy risks
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?
Zhang, Y., Deng, X., Zhongyi, G., Chen, Y., Xu, K., Li, Q., & Wu, J. (2025). Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.07176
How many times has this paper been cited?
16 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?
Yixiang Zhang, Xinhao Deng, Gu, Zhongyi, Yihao Chen, Ke Xu, Qi Li, Jianping Wu.
What is the DOI of this paper?
10.48550/arxiv.2510.07176, permanently at https://doi.org/10.48550/arxiv.2510.07176. 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.