Dissertation · 2025

An empirical study of GPU cache side-channel leakage in large language model inference

Yahya Al-Eryani

Aaltodoc (Aalto University) · Published 29 December 2025

View at the publisherCite this paper

In brief

“An empirical study of GPU cache side-channel leakage in large language model inference” is a 2025 dissertation by Yahya Al-Eryani, published in Aaltodoc (Aalto University). OpenAlex counts 0 citations as of 19 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
0
Authors
1

Abstract

Large language models (LLMs) are typically served on shared graphics processing unit (GPU) hardware to achieve high throughput while meeting the latency requirements of interactive applications. Although such deployments are carefully engineered for efficiency, their reliance on shared microarchitectural resources raises concerns about unintended information leakage. This thesis examines whether GPU microarchitectural side channels, particularly… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

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

APA 7

Al-Eryani, Y. (2025). An empirical study of GPU cache side-channel leakage in large language model inference. Aaltodoc (Aalto University). https://aaltodoc.aalto.fi/handle/123456789/142256

MLA 9

Al-Eryani, Yahya. “An empirical study of GPU cache side-channel leakage in large language model inference.” Aaltodoc (Aalto University), 2025. https://aaltodoc.aalto.fi/handle/123456789/142256.

Chicago

Al-Eryani, Yahya. 2025. “An empirical study of GPU cache side-channel leakage in large language model inference.” Aaltodoc (Aalto University). https://aaltodoc.aalto.fi/handle/123456789/142256.

Harvard

Al-Eryani, Y. (2025) ‘An empirical study of GPU cache side-channel leakage in large language model inference’, Aaltodoc (Aalto University). Available at: https://aaltodoc.aalto.fi/handle/123456789/142256.

IEEE

Y. Al-Eryani, “An empirical study of GPU cache side-channel leakage in large language model inference,” Aaltodoc (Aalto University), 2025.

BibTeX

@phdthesis{aleryani2025empirical,
  title     = {{An empirical study of GPU cache side-channel leakage in large language model inference}},
  author    = {Al-Eryani, Yahya},
  year      = {2025},
  url       = {https://aaltodoc.aalto.fi/handle/123456789/142256}
}

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

Topic and keywords

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

  • large language model inference
  • microarchitectural side channels
  • model fingerprinting
  • NVIDIA GPUs
  • hardware security

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?

Al-Eryani, Y. (2025). An empirical study of GPU cache side-channel leakage in large language model inference. Aaltodoc (Aalto University). https://aaltodoc.aalto.fi/handle/123456789/142256

How many times has this paper been cited?

0 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?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Yahya Al-Eryani.

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.