Journal article · 2025 · Open access

Adversarial prompt and fine-tuning attacks threaten medical large language models

Yifan Yang, Qiao Jin, Furong Huang, Zhiyong Lu

Nature Communications, 16(1), 9011 · Published 9 October 2025 · DOI 10.1038/s41467-025-64062-1

Open PDFView at the publisherCite this paper

In brief

“Adversarial prompt and fine-tuning attacks threaten medical large language models” is a 2025 journal article by Yifan Yang and 3 co-authors, published in Nature Communications. OpenAlex counts 59 citations as of 19 November 2026, which puts it in the top 5% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Nature Communications.

Citations
59
Most cited in
2026 (48)
Field-weighted impact
11.28
References
34
Authors
4

Abstract

The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses a significant threat, potentially leading to harmful outcomes in delicate medical contexts. This study investigates the vulnerability of LLMs to two types of adversarial attacks-prompt injections with malicious instructions and fine-tuning with poisoned samples-across three medical tasks: disease prevention, diagnosis, and treatment. Utilizing real-world patient data, we demonstrate that both open-source and proprietary LLMs are vulnerable to malicious manipulation across multiple tasks. We discover that while integrating poisoned data does not markedly degrade overall model performance on medical benchmarks, it can lead to noticeable shifts in fine-tuned model weights, suggesting a potential pathway for detecting and countering model attacks. This research highlights the urgent need for robust security measures and the development of defensive mechanisms to safeguard LLMs in medical applications, to ensure their safe and effective deployment in healthcare settings.

Cite this paper

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

APA 7

Yang, Y., Jin, Q., Huang, F., & Lu, Z. (2025). Adversarial prompt and fine-tuning attacks threaten medical large language models. Nature Communications, 16(1), 9011. https://doi.org/10.1038/s41467-025-64062-1

MLA 9

Yang, Yifan, et al. “Adversarial prompt and fine-tuning attacks threaten medical large language models.” Nature Communications, vol. 16, no. 1, 2025, p. 9011. https://doi.org/10.1038/s41467-025-64062-1.

Chicago

Yang, Yifan, Qiao Jin, Furong Huang, and Zhiyong Lu. 2025. “Adversarial prompt and fine-tuning attacks threaten medical large language models.” Nature Communications 16 (1): 9011. https://doi.org/10.1038/s41467-025-64062-1.

Harvard

Yang, Y. et al. (2025) ‘Adversarial prompt and fine-tuning attacks threaten medical large language models’, Nature Communications, 16(1), p. 9011. doi:10.1038/s41467-025-64062-1.

IEEE

Y. Yang, Q. Jin, F. Huang, and Z. Lu, “Adversarial prompt and fine-tuning attacks threaten medical large language models,” Nature Communications, vol. 16, no. 1, p. 9011, 2025, doi: 10.1038/s41467-025-64062-1.

BibTeX

@article{yang2025adversarial,
  title     = {{Adversarial prompt and fine-tuning attacks threaten medical large language models}},
  author    = {Yang, Yifan and Jin, Qiao and Huang, Furong and Lu, Zhiyong},
  journal   = {Nature Communications},
  year      = {2025},
  volume    = {16},
  number    = {1},
  pages     = {9011},
  doi       = {10.1038/s41467-025-64062-1},
  url       = {https://doi.org/10.1038/s41467-025-64062-1}
}

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

Citations by year

YearCitationsShare of the best year
202433
202588
20264848

Its field-weighted citation impact is 11.28: it has been cited 11.28 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • adversarial attacks
  • large language models
  • prompt injection
  • data poisoning
  • fine-tuning attacks
  • disease diagnosis
  • treatment guidelines
  • disease prevention

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?

Yang, Y., Jin, Q., Huang, F., & Lu, Z. (2025). Adversarial prompt and fine-tuning attacks threaten medical large language models. Nature Communications, 16(1), 9011. https://doi.org/10.1038/s41467-025-64062-1

How many times has this paper been cited?

59 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 Nature Communications: sign in and open the PDF from this page.

Who wrote this paper?

Yifan Yang, Qiao Jin, Furong Huang, Zhiyong Lu.

What is the DOI of this paper?

10.1038/s41467-025-64062-1, permanently at https://doi.org/10.1038/s41467-025-64062-1. 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.