Preprint · 2023 · Open access

Privacy in Large Language Models: Attacks, Defenses and Future Directions

Haoran Li, Yulin Chen, Jinglong Luo, Wang, Jiecong, Peng, Hao, Yan Kang, Xiaojin Zhang, Qi Hu, Chunkit Chan, Xu, Zenglin, Hooi, Bryan, Yangqiu Song

arXiv (Cornell University) · Published 16 October 2023 · DOI 10.48550/arxiv.2310.10383

Open PDFView at the publisherCite this paper

In brief

“Privacy in Large Language Models: Attacks, Defenses and Future Directions” is a 2023 preprint by Haoran Li and 11 co-authors, published in arXiv (Cornell University). OpenAlex counts 185 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
185
Most cited in
2025 (74)
References
275
Authors
12

Abstract

The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on massive textual data, have brought unparalleled accessibility and usability for both models and users. On the other hand, unrestricted access to these models can also introduce potential malicious and unintentional privacy risks. Despite ongoing efforts to address the safety and privacy concerns associated with LLMs, the problem remains unresolved. In this paper, we provide a comprehensive analysis of the current privacy attacks targeting LLMs and categorize them according to the adversary's assumed capabilities to shed light on the potential vulnerabilities present in LLMs. Then, we present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks. Beyond existing works, we identify upcoming privacy concerns as LLMs evolve. Lastly, we point out several potential avenues for future exploration.

Cite this paper

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

APA 7

Li, H., Chen, Y., Luo, J., Jiecong, W., Hao, P., Kang, Y., Zhang, X., Hu, Q., Chan, C., Zenglin, X., Bryan, H., & Song, Y. (2023). Privacy in Large Language Models: Attacks, Defenses and Future Directions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.10383

MLA 9

Li, Haoran, et al. “Privacy in Large Language Models: Attacks, Defenses and Future Directions.” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2310.10383.

Chicago

Li, Haoran, Yulin Chen, Jinglong Luo, Wang, Jiecong, Peng, Hao, Yan Kang, Xiaojin Zhang, et al. 2023. “Privacy in Large Language Models: Attacks, Defenses and Future Directions.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.10383.

Harvard

Li, H. et al. (2023) ‘Privacy in Large Language Models: Attacks, Defenses and Future Directions’, arXiv (Cornell University). doi:10.48550/arxiv.2310.10383.

IEEE

H. Li et al., “Privacy in Large Language Models: Attacks, Defenses and Future Directions,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2310.10383.

BibTeX

@misc{li2023privacy,
  title     = {{Privacy in Large Language Models: Attacks, Defenses and Future Directions}},
  author    = {Li, Haoran and Chen, Yulin and Luo, Jinglong and Jiecong, Wang, and Hao, Peng, and Kang, Yan and Zhang, Xiaojin and Hu, Qi and Chan, Chunkit and Zenglin, Xu, and Bryan, Hooi, and Song, Yangqiu},
  howpublished = {arXiv (Cornell University)},
  year      = {2023},
  doi       = {10.48550/arxiv.2310.10383},
  url       = {https://doi.org/10.48550/arxiv.2310.10383}
}

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

Citations by year

YearCitationsShare of the best year
202366
20244949
20257474
20265656

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • large language models
  • privacy attacks
  • privacy defenses
  • adversarial attacks
  • LLM vulnerabilities
  • adversary capabilities
  • privacy risks

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?

Li, H., Chen, Y., Luo, J., Jiecong, W., Hao, P., Kang, Y., Zhang, X., Hu, Q., Chan, C., Zenglin, X., Bryan, H., & Song, Y. (2023). Privacy in Large Language Models: Attacks, Defenses and Future Directions. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.10383

How many times has this paper been cited?

185 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?

Haoran Li, Yulin Chen, Jinglong Luo, Wang, Jiecong, Peng, Hao, Yan Kang, Xiaojin Zhang, Qi Hu, Chunkit Chan, Xu, Zenglin, Hooi, Bryan, Yangqiu Song.

What is the DOI of this paper?

10.48550/arxiv.2310.10383, permanently at https://doi.org/10.48550/arxiv.2310.10383. 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.