Preprint · 2024 · Open access

Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer

Avisha Das, Amara Tariq, Felipe Batalini, Boddhisattwa Dhara, Imon Banerjee

medRxiv, 2024, 339–348 · Published 21 March 2024 · DOI 10.1101/2024.03.20.24304627

Open PDFView at the publisherCite this paper

In brief

“Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer” is a 2024 preprint by Avisha Das and 4 co-authors, published in medRxiv. OpenAlex counts 42 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at medRxiv.

Citations
42
Most cited in
2025 (25)
References
20
Authors
5

Abstract

Training Large Language Models (LLMs) with billions of parameters on a dataset and publishing the model for public access is the current standard practice. Despite their transformative impact on natural language processing (NLP), public LLMs present notable vulnerabilities given the source of training data is often web-based or crowdsourced, and hence can be manipulated by perpetrators. We delve into the vulnerabilities of clinical LLMs, particularly BioGPT which is trained on publicly available biomedical literature and clinical notes from MIMIC-III, in the realm of data poisoning attacks. Exploring susceptibility to data poisoning-based attacks on de-identified breast cancer clinical notes, our approach is the first one to assess the extent of such attacks and our findings reveal successful manipulation of LLM outputs. Through this work, we emphasize on the urgency of comprehending these vulnerabilities in LLMs, and encourage the mindful and responsible usage of LLMs in the clinical domain.

Cite this paper

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

APA 7

Das, A., Tariq, A., Batalini, F., Dhara, B., & Banerjee, I. (2024). Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer. medRxiv, 2024, 339–348. https://doi.org/10.1101/2024.03.20.24304627

MLA 9

Das, Avisha, et al. “Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer.” medRxiv, vol. 2024, 2024, pp. 339–348. https://doi.org/10.1101/2024.03.20.24304627.

Chicago

Das, Avisha, Amara Tariq, Felipe Batalini, Boddhisattwa Dhara, and Imon Banerjee. 2024. “Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer.” medRxiv 2024: 339–348. https://doi.org/10.1101/2024.03.20.24304627.

Harvard

Das, A. et al. (2024) ‘Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer’, medRxiv, 2024, pp. 339–348. doi:10.1101/2024.03.20.24304627.

IEEE

A. Das, A. Tariq, F. Batalini, B. Dhara, and I. Banerjee, “Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer,” medRxiv, vol. 2024, pp. 339–348, 2024, doi: 10.1101/2024.03.20.24304627.

BibTeX

@misc{das2024exposing,
  title     = {{Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer}},
  author    = {Das, Avisha and Tariq, Amara and Batalini, Felipe and Dhara, Boddhisattwa and Banerjee, Imon},
  howpublished = {medRxiv},
  year      = {2024},
  volume    = {2024},
  pages     = {339--348},
  doi       = {10.1101/2024.03.20.24304627},
  url       = {https://doi.org/10.1101/2024.03.20.24304627}
}

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

Citations by year

YearCitationsShare of the best year
202466
20252525
20261111

Topic and keywords

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

  • data poisoning
  • large language models
  • BioGPT
  • breast cancer
  • clinical notes
  • MIMIC-III
  • LLM vulnerabilities
  • biomedical literature

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?

Das, A., Tariq, A., Batalini, F., Dhara, B., & Banerjee, I. (2024). Exposing Vulnerabilities in Clinical LLMs Through Data Poisoning Attacks: Case Study in Breast Cancer. medRxiv, 2024, 339–348. https://doi.org/10.1101/2024.03.20.24304627

How many times has this paper been cited?

42 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 medRxiv: sign in and open the PDF from this page.

Who wrote this paper?

Avisha Das, Amara Tariq, Felipe Batalini, Boddhisattwa Dhara, Imon Banerjee.

What is the DOI of this paper?

10.1101/2024.03.20.24304627, permanently at https://doi.org/10.1101/2024.03.20.24304627. 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.