Conference paper · 2025 · Open access
Exploring Membership Inference Vulnerabilities in Clinical Large Language Models
IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), 509–516 · Published 12 November 2025 · DOI 10.1109/tps-isa67132.2025.00061
In brief
“Exploring Membership Inference Vulnerabilities in Clinical Large Language Models” is a 2025 conference paper by Alexander Nemecek and 6 co-authors, published in IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA). OpenAlex counts 2 citations as of 19 November 2026, which puts it in the top 6% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 2
- Most cited in
- 2026 (2)
- Field-weighted impact
- 0.42
- References
- 40
- Authors
- 7
Abstract
As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the healthcare sector. Fine-tuning LLMs on sensitive electronic health record (EHR) data improves domain alignment but also raises the risk of exposing patient information through model behaviors. In this work-in-progress, we present an exploratory empirical study on membership inference vulnerabilities in clinical LLMs, focusing on whether adversaries can infer if specific patient records were used during model training. Using a state-of-the-art clinical question-answering model, Llemr, we evaluate both canonical loss-based attacks and a domain-motivated paraphrasing-based perturbation strategy that more realistically reflects clinical adversarial conditions. Our preliminary findings reveal limited but measurable membership leakage, suggesting that current clinical LLMs provide partial resistance yet remain susceptible to subtle privacy risks that could undermine trust in clinical AI adoption. These results motivate continued development of context-aware, domain-specific privacy evaluations and defenses such as differential privacy fine-tuning and paraphraseaware training, to strengthen the security and trustworthiness of healthcare AI systems.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Nemecek, A., Yun, Z., Rahmani, Z., Harel, Y., Chaudhary, V., Sharif, M., & Ayday, E. (2025). Exploring Membership Inference Vulnerabilities in Clinical Large Language Models. IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), 509–516. https://doi.org/10.1109/tps-isa67132.2025.00061
MLA 9
Nemecek, Alexander, et al. “Exploring Membership Inference Vulnerabilities in Clinical Large Language Models.” IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), 2025, pp. 509–516. https://doi.org/10.1109/tps-isa67132.2025.00061.
Chicago
Nemecek, Alexander, Zebin Yun, Zahra Rahmani, Yaniv Harel, Vipin Chaudhary, Mahmood Sharif, and Erman Ayday. 2025. “Exploring Membership Inference Vulnerabilities in Clinical Large Language Models.” IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA): 509–516. https://doi.org/10.1109/tps-isa67132.2025.00061.
Harvard
Nemecek, A. et al. (2025) ‘Exploring Membership Inference Vulnerabilities in Clinical Large Language Models’, IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), pp. 509–516. doi:10.1109/tps-isa67132.2025.00061.
IEEE
A. Nemecek et al., “Exploring Membership Inference Vulnerabilities in Clinical Large Language Models,” IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), pp. 509–516, 2025, doi: 10.1109/tps-isa67132.2025.00061.
BibTeX
@inproceedings{nemecek2025exploring,
title = {{Exploring Membership Inference Vulnerabilities in Clinical Large Language Models}},
author = {Nemecek, Alexander and Yun, Zebin and Rahmani, Zahra and Harel, Yaniv and Chaudhary, Vipin and Sharif, Mahmood and Ayday, Erman},
booktitle = {IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)},
year = {2025},
pages = {509--516},
doi = {10.1109/tps-isa67132.2025.00061},
url = {https://doi.org/10.1109/tps-isa67132.2025.00061}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- membership inference attacks
- clinical large language models
- privacy leakage
- electronic health records
- medical question answering
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Nemecek, A., Yun, Z., Rahmani, Z., Harel, Y., Chaudhary, V., Sharif, M., & Ayday, E. (2025). Exploring Membership Inference Vulnerabilities in Clinical Large Language Models. IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), 509–516. https://doi.org/10.1109/tps-isa67132.2025.00061
How many times has this paper been cited?
2 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?
Alexander Nemecek, Zebin Yun, Zahra Rahmani, Yaniv Harel, Vipin Chaudhary, Mahmood Sharif, Erman Ayday.
What is the DOI of this paper?
10.1109/tps-isa67132.2025.00061, permanently at https://doi.org/10.1109/tps-isa67132.2025.00061. 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.