Preprint · 2026 · Open access
A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
arXiv (Cornell University) · Published 25 September 2026 · DOI 10.48550/arxiv.2609.31877
In brief
“A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services” is a 2026 preprint by Shahrooz Pouryousef and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2026 (3)
- References
- 28
- Authors
- 7
Abstract
Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite encryption. From packet sizes, directions, timing, and burst structure alone, a passive local observer can infer the serving model, the user's prompt category, and the task executed by a collaborative multi-agent system. Yet current evidence is fragmented across separate datasets and settings, limiting reproducibility and comparison. We present, to our knowledge, the first unified measurement study and public benchmark of encrypted LLM traffic across both user--LLM and multi-agent executions. The large-scale benchmark contains 60,000 user--LLM interactions across 10 models and 6 prompt categories, plus 2,838 multi-agent executions covering 10 task categories and two coordination topologies. Using only encrypted packet metadata, we assess the risk of traffic analysis attack by characterizing traffic signatures, identifying the features most associated with leakage, and testing robustness under prompt reformulation, decoding-temperature changes, larger candidate model sets, and partial traffic observation. Model fingerprinting achieves 97.7\% balanced accuracy, prompt-category fingerprinting reaches 76.7\% mean accuracy, and multi-agent task fingerprinting achieves up to 90.7\% accuracy. Prompt reformulation weakens but does not remove model-specific leakage, and task fingerprints remain detectable even from a single agent's traffic.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Pouryousef, S., Lopez, J., Nowmi, S. R., Kamol, M. M., Hossain, M., Tran, M., & Rahman, M. S. (2026). A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.31877
MLA 9
Pouryousef, Shahrooz, et al. “A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.31877.
Chicago
Pouryousef, Shahrooz, Jesus Lopez, Saeefa Rubaiyet Nowmi, Md Mahmuduzzaman Kamol, Moinul Hossain, Muoi Tran, and Mohammad Saidur Rahman. 2026. “A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.31877.
Harvard
Pouryousef, S. et al. (2026) ‘A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services’, arXiv (Cornell University). doi:10.48550/arxiv.2609.31877.
IEEE
S. Pouryousef et al., “A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.31877.
BibTeX
@misc{pouryousef2026large,
title = {{A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services}},
author = {Pouryousef, Shahrooz and Lopez, Jesus and Nowmi, Saeefa Rubaiyet and Kamol, Md Mahmuduzzaman and Hossain, Moinul and Tran, Muoi and Rahman, Mohammad Saidur},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2609.31877},
url = {https://doi.org/10.48550/arxiv.2609.31877}
}
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
- traffic analysis attacks
- large language models
- multi-agent systems
- model fingerprinting
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?
Pouryousef, S., Lopez, J., Nowmi, S. R., Kamol, M. M., Hossain, M., Tran, M., & Rahman, M. S. (2026). A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.31877
How many times has this paper been cited?
3 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?
Shahrooz Pouryousef, Jesus Lopez, Saeefa Rubaiyet Nowmi, Md Mahmuduzzaman Kamol, Moinul Hossain, Muoi Tran, Mohammad Saidur Rahman.
What is the DOI of this paper?
10.48550/arxiv.2609.31877, permanently at https://doi.org/10.48550/arxiv.2609.31877. 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.