Journal article · 2025 · Open access

A survey on privacy risks and protection in large language models

Kang Chen, Xiuze Zhou, Yuanguo Lin, Shibo Feng, Li Shen, Pengcheng Wu

Journal of King Saud University - Computer and Information Sciences, 37(7) · Published 18 August 2025 · DOI 10.1007/s44443-025-00177-1

Open PDFView at the publisherCite this paper

In brief

“A survey on privacy risks and protection in large language models” is a 2025 journal article by Kang Chen and 5 co-authors, published in Journal of King Saud University - Computer and Information Sciences. OpenAlex counts 97 citations as of 19 November 2026, which puts it in the top 1% of works published in 2025 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of King Saud University - Computer and Information Sciences.

Citations
97
Most cited in
2026 (77)
Field-weighted impact
17.12
References
124
Authors
6

Abstract

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. First, we analyze privacy leakage and attacks in LLMs, focusing on how these models unintentionally expose sensitive information through techniques such as model inversion, training data extraction, and membership inference. We investigate the mechanisms of privacy leakage, including the unauthorized extraction of training data and the potential exploitation of these vulnerabilities by malicious actors. Next, we review existing privacy protection against such risks, such as inference detection, federated learning, backdoor mitigation, and confidential computing, and assess their effectiveness in preventing privacy leakage. Furthermore, we highlight key practical challenges and propose future research directions to develop secure and privacy-preserving LLMs, emphasizing privacy risk assessment, secure knowledge transfer between models, practical deployment and trade-offs, and interdisciplinary frameworks for privacy governance. Ultimately, this survey aims to establish a roadmap for addressing escalating privacy challenges in the LLMs domain.

Cite this paper

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

APA 7

Chen, K., Zhou, X., Lin, Y., Feng, S., Shen, L., & Wu, P. (2025). A survey on privacy risks and protection in large language models. Journal of King Saud University - Computer and Information Sciences, 37(7). https://doi.org/10.1007/s44443-025-00177-1

MLA 9

Chen, Kang, et al. “A survey on privacy risks and protection in large language models.” Journal of King Saud University - Computer and Information Sciences, vol. 37, no. 7, 2025. https://doi.org/10.1007/s44443-025-00177-1.

Chicago

Chen, Kang, Xiuze Zhou, Yuanguo Lin, Shibo Feng, Li Shen, and Pengcheng Wu. 2025. “A survey on privacy risks and protection in large language models.” Journal of King Saud University - Computer and Information Sciences 37 (7). https://doi.org/10.1007/s44443-025-00177-1.

Harvard

Chen, K. et al. (2025) ‘A survey on privacy risks and protection in large language models’, Journal of King Saud University - Computer and Information Sciences, 37(7). doi:10.1007/s44443-025-00177-1.

IEEE

K. Chen, X. Zhou, Y. Lin, S. Feng, L. Shen, and P. Wu, “A survey on privacy risks and protection in large language models,” Journal of King Saud University - Computer and Information Sciences, vol. 37, no. 7, 2025, doi: 10.1007/s44443-025-00177-1.

BibTeX

@article{chen2025survey,
  title     = {{A survey on privacy risks and protection in large language models}},
  author    = {Chen, Kang and Zhou, Xiuze and Lin, Yuanguo and Feng, Shibo and Shen, Li and Wu, Pengcheng},
  journal   = {Journal of King Saud University - Computer and Information Sciences},
  year      = {2025},
  volume    = {37},
  number    = {7},
  doi       = {10.1007/s44443-025-00177-1},
  url       = {https://doi.org/10.1007/s44443-025-00177-1}
}

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 risks
  • privacy leakage
  • membership inference attacks
  • model inversion attacks
  • training data extraction
  • federated learning
  • backdoor mitigation

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?

Chen, K., Zhou, X., Lin, Y., Feng, S., Shen, L., & Wu, P. (2025). A survey on privacy risks and protection in large language models. Journal of King Saud University - Computer and Information Sciences, 37(7). https://doi.org/10.1007/s44443-025-00177-1

How many times has this paper been cited?

97 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 Journal of King Saud University - Computer and Information Sciences: sign in and open the PDF from this page.

Who wrote this paper?

Kang Chen, Xiuze Zhou, Yuanguo Lin, Shibo Feng, Li Shen, Pengcheng Wu.

What is the DOI of this paper?

10.1007/s44443-025-00177-1, permanently at https://doi.org/10.1007/s44443-025-00177-1. 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.