Journal article · 2026 · Open access
Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions
International Journal of Advanced Computer Science and Applications, 17(6) · Published 1 January 2026 · DOI 10.14569/ijacsa.2026.0170604
In brief
“Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions” is a 2026 journal article by Yassine Chahid and 3 co-authors, published in International Journal of Advanced Computer Science and Applications. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at International Journal of Advanced Computer Science and Applications.
- Citations
- 0
- References
- 40
- Authors
- 4
Abstract
The increasing adoption of large language mod-els (LLMs) and domain-adapted transformers in healthcare has created a new privacy challenge: fine-tuned models may memorize rare clinical strings and later reveal them through generation or scoring behavior. A controlled study of privacy leakage and memorization in clinical language models trained on narrative transcriptions is presented. A canary-based audit pipeline was instantiated on a 4,000-note subset of the Medical Transcriptions (MTSamples) corpus, with 40 synthetic secrets injected only into the training partition and evaluated using three complementary attack families: prompt extraction, exposure-style ranking, and reference-based membership inference. Two experiments are reported. Experiment I compares baseline fine-tuning, early stopping, and a conservative regularized training profile combining lower learning rate, higher weight decay, and partial layer freezing. Experiment II fixes the training protocol and compares DistilGPT2, GPT-2, and BioGPT. A clear privacy-utility tension was observed. In Experiment I, early stopping produced the best held-out language-model utility, whereas the combined regularized profile eliminated observed prompt leak-age and reduced membership-inference strength, at the cost of worse perplexity. In Experiment II, stronger and more domain-specialized backbones achieved better clinical language modeling but also exhibited higher leakage and stronger membership-inference signals, with BioGPT yielding the strongest utility and the highest privacy risk under the evaluated attacks. These results indicate that privacy auditing should accompany utility evaluation in clinical LLM adaptation, and that backbone choice can materially affect memorization risk in this controlled setting.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chahid, Y., Chahid, A., Chahid, I., & Elmiad, A. K. (2026). Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions. International Journal of Advanced Computer Science and Applications, 17(6). https://doi.org/10.14569/ijacsa.2026.0170604
MLA 9
Chahid, Yassine, et al. “Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions.” International Journal of Advanced Computer Science and Applications, vol. 17, no. 6, 2026. https://doi.org/10.14569/ijacsa.2026.0170604.
Chicago
Chahid, Yassine, Anas Chahid, Ismail Chahid, and Aissa Kerkour Elmiad. 2026. “Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions.” International Journal of Advanced Computer Science and Applications 17 (6). https://doi.org/10.14569/ijacsa.2026.0170604.
Harvard
Chahid, Y. et al. (2026) ‘Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions’, International Journal of Advanced Computer Science and Applications, 17(6). doi:10.14569/ijacsa.2026.0170604.
IEEE
Y. Chahid, A. Chahid, I. Chahid, and A. K. Elmiad, “Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions,” International Journal of Advanced Computer Science and Applications, vol. 17, no. 6, 2026, doi: 10.14569/ijacsa.2026.0170604.
BibTeX
@article{chahid2026privacy,
title = {{Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions}},
author = {Chahid, Yassine and Chahid, Anas and Chahid, Ismail and Elmiad, Aissa Kerkour},
journal = {International Journal of Advanced Computer Science and Applications},
year = {2026},
volume = {17},
number = {6},
doi = {10.14569/ijacsa.2026.0170604},
url = {https://doi.org/10.14569/ijacsa.2026.0170604}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- privacy leakage
- memorization
- clinical language models
- fine-tuning
- membership inference
- early stopping
- regularization
- weight decay
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?
Chahid, Y., Chahid, A., Chahid, I., & Elmiad, A. K. (2026). Privacy Leakage and Memorization in Fine-Tuned Clinical Language Models: A Controlled Study of Defenses and Backbone Choice on Clinical Narrative Transcriptions. International Journal of Advanced Computer Science and Applications, 17(6). https://doi.org/10.14569/ijacsa.2026.0170604
How many times has this paper been cited?
0 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 International Journal of Advanced Computer Science and Applications: sign in and open the PDF from this page.
Who wrote this paper?
Yassine Chahid, Anas Chahid, Ismail Chahid, Aissa Kerkour Elmiad.
What is the DOI of this paper?
10.14569/ijacsa.2026.0170604, permanently at https://doi.org/10.14569/ijacsa.2026.0170604. 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.