Preprint · 2021 · Open access

Membership Inference Attack Susceptibility of Clinical Language Models

Abhyuday Jagannatha, Bhanu Pratap Singh Rawat, Hong Qing Yu

arXiv (Cornell University) · Published 16 April 2021 · DOI 10.48550/arxiv.2104.08305

Open PDFView at the publisherCite this paper

In brief

“Membership Inference Attack Susceptibility of Clinical Language Models” is a 2021 preprint by Abhyuday Jagannatha and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 108 citations as of 19 November 2026. It is open access under a public domain licence: the full text is free to read at arXiv (Cornell University).

Citations
108
Most cited in
2025 (34)
References
27
Authors
3

Abstract

Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language processing tasks. In this work, we investigate the risks of training-data leakage through white-box or black-box access to CLMs. We design and employ membership inference attacks to estimate the empirical privacy leaks for model architectures like BERT and GPT2. We show that membership inference attacks on CLMs lead to non-trivial privacy leakages of up to 7%. Our results show that smaller models have lower empirical privacy leakages than larger ones, and masked LMs have lower leakages than auto-regressive LMs. We further show that differentially private CLMs can have improved model utility on clinical domain while ensuring low empirical privacy leakage. Lastly, we also study the effects of group-level membership inference and disease rarity on CLM privacy leakages.

Cite this paper

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

APA 7

Jagannatha, A., Rawat, B. P. S., & Yu, H. Q. (2021). Membership Inference Attack Susceptibility of Clinical Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2104.08305

MLA 9

Jagannatha, Abhyuday, et al. “Membership Inference Attack Susceptibility of Clinical Language Models.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2104.08305.

Chicago

Jagannatha, Abhyuday, Bhanu Pratap Singh Rawat, and Hong Qing Yu. 2021. “Membership Inference Attack Susceptibility of Clinical Language Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2104.08305.

Harvard

Jagannatha, A., Rawat, B. P. S. and Yu, H. Q. (2021) ‘Membership Inference Attack Susceptibility of Clinical Language Models’, arXiv (Cornell University). doi:10.48550/arxiv.2104.08305.

IEEE

A. Jagannatha, B. P. S. Rawat, and H. Q. Yu, “Membership Inference Attack Susceptibility of Clinical Language Models,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2104.08305.

BibTeX

@misc{jagannatha2021membership,
  title     = {{Membership Inference Attack Susceptibility of Clinical Language Models}},
  author    = {Jagannatha, Abhyuday and Rawat, Bhanu Pratap Singh and Yu, Hong Qing},
  howpublished = {arXiv (Cornell University)},
  year      = {2021},
  doi       = {10.48550/arxiv.2104.08305},
  url       = {https://doi.org/10.48550/arxiv.2104.08305}
}

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

Citations by year

YearCitationsShare of the best year
202277
20231919
20242828
20253434
20262020

Topic and keywords

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

  • membership inference attacks
  • clinical language models
  • differential privacy
  • BERT
  • GPT-2
  • masked language models
  • autoregressive language models
  • clinical data privacy

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?

Jagannatha, A., Rawat, B. P. S., & Yu, H. Q. (2021). Membership Inference Attack Susceptibility of Clinical Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2104.08305

How many times has this paper been cited?

108 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?

Abhyuday Jagannatha, Bhanu Pratap Singh Rawat, Hong Qing Yu.

What is the DOI of this paper?

10.48550/arxiv.2104.08305, permanently at https://doi.org/10.48550/arxiv.2104.08305. 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.