Preprint · 2023 · Open access

Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey

Victoria Louise Smith, Ali Shahin Shamsabadi, Carolyn Ashurst, Adrian Weller

arXiv (Cornell University) · Published 27 September 2023 · DOI 10.48550/arxiv.2310.01424

Open PDFView at the publisherCite this paper

In brief

“Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey” is a 2023 preprint by Victoria Louise Smith and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 71 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
71
Most cited in
2025 (33)
References
122
Authors
4

Abstract

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public. However, training data memorization in Machine Learning models scales with model size, particularly concerning for LLMs. Memorized text sequences have the potential to be directly leaked from LLMs, posing a serious threat to data privacy. Various techniques have been developed to attack LLMs and extract their training data. As these models continue to grow, this issue becomes increasingly critical. To help researchers and policymakers understand the state of knowledge around privacy attacks and mitigations, including where more work is needed, we present the first SoK on data privacy for LLMs. We (i) identify a taxonomy of salient dimensions where attacks differ on LLMs, (ii) systematize existing attacks, using our taxonomy of dimensions to highlight key trends, (iii) survey existing mitigation strategies, highlighting their strengths and limitations, and (iv) identify key gaps, demonstrating open problems and areas for concern.

Cite this paper

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

APA 7

Smith, V. L., Shamsabadi, A. S., Ashurst, C., & Weller, A. (2023). Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.01424

MLA 9

Smith, Victoria Louise, et al. “Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey.” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2310.01424.

Chicago

Smith, Victoria Louise, Ali Shahin Shamsabadi, Carolyn Ashurst, and Adrian Weller. 2023. “Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.01424.

Harvard

Smith, V. L. et al. (2023) ‘Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey’, arXiv (Cornell University). doi:10.48550/arxiv.2310.01424.

IEEE

V. L. Smith, A. S. Shamsabadi, C. Ashurst, and A. Weller, “Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2310.01424.

BibTeX

@misc{smith2023identifying,
  title     = {{Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey}},
  author    = {Smith, Victoria Louise and Shamsabadi, Ali Shahin and Ashurst, Carolyn and Weller, Adrian},
  howpublished = {arXiv (Cornell University)},
  year      = {2023},
  doi       = {10.48550/arxiv.2310.01424},
  url       = {https://doi.org/10.48550/arxiv.2310.01424}
}

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

Citations by year

YearCitationsShare of the best year
202322
20241717
20253333
20261919

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • large language models
  • data privacy
  • training data memorization
  • privacy attacks
  • attack taxonomy
  • data leakage

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?

Smith, V. L., Shamsabadi, A. S., Ashurst, C., & Weller, A. (2023). Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.01424

How many times has this paper been cited?

71 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?

Victoria Louise Smith, Ali Shahin Shamsabadi, Carolyn Ashurst, Adrian Weller.

What is the DOI of this paper?

10.48550/arxiv.2310.01424, permanently at https://doi.org/10.48550/arxiv.2310.01424. 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.