Journal article · 2025 · Open access

The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems

Linke Song, Zixuan Pang, Wenhao Wang, Zihao Wang, Xiaofeng Wang, Hongbo Chen, Wei Song, Yier Jin, Dan Meng, Rui Hou

IEEE Transactions on Information Forensics and Security, 20, 11431–11446 · Published 1 January 2025 · DOI 10.1109/tifs.2025.3622954

Open PDFView at the publisherCite this paper

In brief

“The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems” is a 2025 journal article by Linke Song and 9 co-authors, published in IEEE Transactions on Information Forensics and Security. OpenAlex counts 57 citations as of 19 November 2026, which puts it in the top 8% of works published in 2025 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
57
Most cited in
2026 (41)
Field-weighted impact
20.06
References
35
Authors
10

Abstract

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today’s techniques serving this purpose primarily focus on reducing latency and improving throughput through algorithmic and hardware enhancements, while largely overlooking their privacy side effects, particularly in a multi-user environment. In our research, for the first time, we discovered a set of new timing side channels in LLM systems, arising from shared caches and GPU memory allocations, which can be exploited to infer both confidential system prompts and those issued by other users. These vulnerabilities echo security challenges observed in traditional computing systems, highlighting an urgent need to address potential information leakage in LLM serving infrastructures. In this paper, we report novel attack strategies designed to exploit such timing side channels inherent in LLM deployments, specifically targeting the Key-Value (KV) cache and semantic cache widely used to enhance LLM inference performance. Our approach leverages timing measurements and classification models to detect cache hits, allowing an adversary to infer private prompts with high accuracy. We also propose a token-by-token search algorithm to efficiently recover shared prompt prefixes in the caches, showing the feasibility of stealing system prompts and those produced by peer users. Our experimental studies on black-box testing of popular online LLM services demonstrate that such privacy risks are completely realistic, with significant consequences. Our findings underscore the need for robust mitigation to protect LLM systems against such emerging threats.

Cite this paper

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

APA 7

Song, L., Pang, Z., Wang, W., Wang, Z., Wang, X., Chen, H., Song, W., Jin, Y., Meng, D., & Hou, R. (2025). The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems. IEEE Transactions on Information Forensics and Security, 20, 11431–11446. https://doi.org/10.1109/tifs.2025.3622954

MLA 9

Song, Linke, et al. “The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems.” IEEE Transactions on Information Forensics and Security, vol. 20, 2025, pp. 11431–11446. https://doi.org/10.1109/tifs.2025.3622954.

Chicago

Song, Linke, Zixuan Pang, Wenhao Wang, Zihao Wang, Xiaofeng Wang, Hongbo Chen, Wei Song, Yier Jin, Dan Meng, and Rui Hou. 2025. “The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems.” IEEE Transactions on Information Forensics and Security 20: 11431–11446. https://doi.org/10.1109/tifs.2025.3622954.

Harvard

Song, L. et al. (2025) ‘The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems’, IEEE Transactions on Information Forensics and Security, 20, pp. 11431–11446. doi:10.1109/tifs.2025.3622954.

IEEE

L. Song et al., “The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems,” IEEE Transactions on Information Forensics and Security, vol. 20, pp. 11431–11446, 2025, doi: 10.1109/tifs.2025.3622954.

BibTeX

@article{song2025early,
  title     = {{The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems}},
  author    = {Song, Linke and Pang, Zixuan and Wang, Wenhao and Wang, Zihao and Wang, Xiaofeng and Chen, Hongbo and Song, Wei and Jin, Yier and Meng, Dan and Hou, Rui},
  journal   = {IEEE Transactions on Information Forensics and Security},
  year      = {2025},
  volume    = {20},
  pages     = {11431--11446},
  doi       = {10.1109/tifs.2025.3622954},
  url       = {https://doi.org/10.1109/tifs.2025.3622954}
}

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

Citations by year

YearCitationsShare of the best year
202422
20251414
20264141

Its field-weighted citation impact is 20.06: it has been cited 20.06 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Hardware and Architecture › Security and Verification in Computing

  • timing side channels
  • key-value cache
  • semantic cache
  • information leakage
  • black-box attacks

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?

Song, L., Pang, Z., Wang, W., Wang, Z., Wang, X., Chen, H., Song, W., Jin, Y., Meng, D., & Hou, R. (2025). The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems. IEEE Transactions on Information Forensics and Security, 20, 11431–11446. https://doi.org/10.1109/tifs.2025.3622954

How many times has this paper been cited?

57 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?

Linke Song, Zixuan Pang, Wenhao Wang, Zihao Wang, Xiaofeng Wang, Hongbo Chen, Wei Song, Yier Jin, Dan Meng, Rui Hou.

What is the DOI of this paper?

10.1109/tifs.2025.3622954, permanently at https://doi.org/10.1109/tifs.2025.3622954. 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.