Preprint · 2025 · Open access
Whisper Leak: a side-channel attack on Large Language Models
arXiv (Cornell University) · Published 5 November 2025 · DOI 10.48550/arxiv.2511.03675
In brief
“Whisper Leak: a side-channel attack on Large Language Models” is a 2025 preprint by McDonald, Geoff and Jonathan Bar Or, published in arXiv (Cornell University). OpenAlex counts 19 citations as of 19 November 2026. It is open access under a public domain licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 19
- Most cited in
- 2026 (19)
- References
- 12
- Authors
- 2
Abstract
Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that infers user prompt topics from encrypted LLM traffic by analyzing packet size and timing patterns in streaming responses. Despite TLS encryption protecting content, these metadata patterns leak sufficient information to enable topic classification. We demonstrate the attack across 28 popular LLMs from major providers, achieving near-perfect classification (often >98% AUPRC) and high precision even at extreme class imbalance (10,000:1 noise-to-target ratio). For many models, we achieve 100% precision in identifying sensitive topics like "money laundering" while recovering 5-20% of target conversations. This industry-wide vulnerability poses significant risks for users under network surveillance by ISPs, governments, or local adversaries. We evaluate three mitigation strategies - random padding, token batching, and packet injection - finding that while each reduces attack effectiveness, none provides complete protection. Through responsible disclosure, we have collaborated with providers to implement initial countermeasures. Our findings underscore the need for LLM providers to address metadata leakage as AI systems handle increasingly sensitive information.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Geoff, M., & Or, J. B. (2025). Whisper Leak: a side-channel attack on Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2511.03675
MLA 9
Geoff, McDonald,, and Jonathan Bar Or. “Whisper Leak: a side-channel attack on Large Language Models.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2511.03675.
Chicago
Geoff, McDonald, and Jonathan Bar Or. 2025. “Whisper Leak: a side-channel attack on Large Language Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2511.03675.
Harvard
Geoff, M. and Or, J. B. (2025) ‘Whisper Leak: a side-channel attack on Large Language Models’, arXiv (Cornell University). doi:10.48550/arxiv.2511.03675.
IEEE
M. Geoff and J. B. Or, “Whisper Leak: a side-channel attack on Large Language Models,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2511.03675.
BibTeX
@misc{geoff2025whisper,
title = {{Whisper Leak: a side-channel attack on Large Language Models}},
author = {Geoff, McDonald, and Or, Jonathan Bar},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2511.03675},
url = {https://doi.org/10.48550/arxiv.2511.03675}
}
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
- side-channel attacks
- large language models
- topic inference
- privacy
- network surveillance
- mitigation measures
- packet injection
- money laundering detection
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?
Geoff, M., & Or, J. B. (2025). Whisper Leak: a side-channel attack on Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2511.03675
How many times has this paper been cited?
19 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?
McDonald, Geoff, Jonathan Bar Or.
What is the DOI of this paper?
10.48550/arxiv.2511.03675, permanently at https://doi.org/10.48550/arxiv.2511.03675. 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.