Report · 2026

Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs

Sri Vikass Jeyaprakash

DR-NTU (Nanyang Technological University) · Published 1 January 2026

View at the publisherCite this paper

In brief

“Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs” is a 2026 report by Sri Vikass Jeyaprakash, published in DR-NTU (Nanyang Technological University). OpenAlex counts 0 citations as of 19 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
0
Authors
1

Abstract

The increased adoption of Large Language Models (LLMs) in healthcare provide newfound areas for innovation and efficiency, yet also introduce significant privacy threats through the inadvertent memorization and generative regurgitation of Protected Health Information (PHI) found in the training data. This project investigates the vulnerability of multiple fine-tuned medical LLMs to text-based generative extraction attacks… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

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

APA 7

Jeyaprakash, S. V. (2026). Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs. DR-NTU (Nanyang Technological University). https://hdl.handle.net/10356/214226

MLA 9

Jeyaprakash, Sri Vikass. “Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs.” DR-NTU (Nanyang Technological University), 2026. https://hdl.handle.net/10356/214226.

Chicago

Jeyaprakash, Sri Vikass. 2026. “Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs.” DR-NTU (Nanyang Technological University). https://hdl.handle.net/10356/214226.

Harvard

Jeyaprakash, S. V. (2026) ‘Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs’, DR-NTU (Nanyang Technological University). Available at: https://hdl.handle.net/10356/214226.

IEEE

S. V. Jeyaprakash, “Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs,” DR-NTU (Nanyang Technological University), 2026.

BibTeX

@article{jeyaprakash2026evaluating,
  title     = {{Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs}},
  author    = {Jeyaprakash, Sri Vikass},
  journal   = {DR-NTU (Nanyang Technological University)},
  year      = {2026},
  url       = {https://hdl.handle.net/10356/214226}
}

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

  • medical large language models
  • privacy attacks
  • membership inference attacks
  • data sanitization
  • named entity recognition

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?

Jeyaprakash, S. V. (2026). Evaluating and mitigating simulated protected health information (PHI) leakage in medical question-answering LLMs. DR-NTU (Nanyang Technological University). https://hdl.handle.net/10356/214226

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?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Sri Vikass Jeyaprakash.

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.