Conference paper · 2025 · Open access
SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
ACM Asia Conference on Computer and Communications Security (ASIA CCS), 425–441 · Published 13 August 2025 · DOI 10.1145/3708821.3733888
In brief
“SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation” is a 2025 conference paper by Yashothara Shanmugarasa and 3 co-authors, published in ACM Asia Conference on Computer and Communications Security (ASIA CCS). OpenAlex counts 60 citations as of 19 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at ACM Asia Conference on Computer and Communications Security (ASIA CCS).
- Citations
- 60
- Most cited in
- 2026 (47)
- Field-weighted impact
- 11.31
- References
- 135
- Authors
- 4
Abstract
Large language models (LLMs) are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer significant technological progress, their development using vast amounts of user data scraped from the web and collected from extensive user interactions poses risks of sensitive information leakage. Most existing surveys focus on the privacy implications of the training data but tend to overlook privacy risks from user interactions and advanced LLM capabilities. This paper aims to fill that gap by providing a comprehensive analysis of privacy in LLMs, categorizing the challenges into four main areas: (i) privacy issues in LLM training data, (ii) privacy challenges associated with user prompts, (iii) privacy vulnerabilities in LLM-generated outputs, and (iv) privacy challenges involving LLM agents. We evaluate the effectiveness and limitations of existing mitigation mechanisms targeting these proposed privacy challenges and identify areas for further research.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Shanmugarasa, Y., Ding, M., Chamikara, M., & Rakotoarivelo, T. (2025). SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation. ACM Asia Conference on Computer and Communications Security (ASIA CCS), 425–441. https://doi.org/10.1145/3708821.3733888
MLA 9
Shanmugarasa, Yashothara, et al. “SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation.” ACM Asia Conference on Computer and Communications Security (ASIA CCS), 2025, pp. 425–441. https://doi.org/10.1145/3708821.3733888.
Chicago
Shanmugarasa, Yashothara, Ming Ding, M.A.P. Chamikara, and Thierry Rakotoarivelo. 2025. “SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation.” ACM Asia Conference on Computer and Communications Security (ASIA CCS): 425–441. https://doi.org/10.1145/3708821.3733888.
Harvard
Shanmugarasa, Y. et al. (2025) ‘SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation’, ACM Asia Conference on Computer and Communications Security (ASIA CCS), pp. 425–441. doi:10.1145/3708821.3733888.
IEEE
Y. Shanmugarasa, M. Ding, M. Chamikara, and T. Rakotoarivelo, “SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation,” ACM Asia Conference on Computer and Communications Security (ASIA CCS), pp. 425–441, 2025, doi: 10.1145/3708821.3733888.
BibTeX
@inproceedings{shanmugarasa2025privacy,
title = {{SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation}},
author = {Shanmugarasa, Yashothara and Ding, Ming and Chamikara, M.A.P. and Rakotoarivelo, Thierry},
booktitle = {ACM Asia Conference on Computer and Communications Security (ASIA CCS)},
year = {2025},
pages = {425--441},
doi = {10.1145/3708821.3733888},
url = {https://doi.org/10.1145/3708821.3733888}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- large language models
- privacy paradox
- privacy risks
- training data privacy
- user prompts
- LLM agents
- privacy leakage
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?
Shanmugarasa, Y., Ding, M., Chamikara, M., & Rakotoarivelo, T. (2025). SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation. ACM Asia Conference on Computer and Communications Security (ASIA CCS), 425–441. https://doi.org/10.1145/3708821.3733888
How many times has this paper been cited?
60 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 ACM Asia Conference on Computer and Communications Security (ASIA CCS): sign in and open the full text from this page.
Who wrote this paper?
Yashothara Shanmugarasa, Ming Ding, M.A.P. Chamikara, Thierry Rakotoarivelo.
What is the DOI of this paper?
10.1145/3708821.3733888, permanently at https://doi.org/10.1145/3708821.3733888. 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.