Paper · 2023 · Open access

Privacy leakages on NLP models and mitigations through a use case on medical data

Gaspard Berthelier, Antoine Boutet, Antoine Richard

HAL, 1–8 · Published 4 July 2023

Open PDFView at the publisherCite this paper

In brief

“Privacy leakages on NLP models and mitigations through a use case on medical data” is a 2023 paper by Gaspard Berthelier and 2 co-authors, published in HAL. OpenAlex counts 2 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at HAL.

Citations
2
Most cited in
2025 (1)
Field-weighted impact
0.13
References
9
Authors
3

Abstract

Patient medical data is extremely sensitive and private, and thus subject to numerous regulations which require anonymization before disseminating the data. The anonymization of medical documents is a complex task but the recent advances in NLP models have shown encouraging results. Nevertheless, privacy risks associated with NLP models may still remain. In this paper, we present the main privacy concerns in NLP and a case study conducted in collaboration with the Hospices Civils de Lyon (HCL) to exploit NLP models to anonymize medical data.

Cite this paper

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

APA 7

Berthelier, G., Boutet, A., & Richard, A. (2023). Privacy leakages on NLP models and mitigations through a use case on medical data. HAL, 1–8. https://inria.hal.science/hal-04138528

MLA 9

Berthelier, Gaspard, et al. “Privacy leakages on NLP models and mitigations through a use case on medical data.” HAL, 2023, pp. 1–8. https://inria.hal.science/hal-04138528.

Chicago

Berthelier, Gaspard, Antoine Boutet, and Antoine Richard. 2023. “Privacy leakages on NLP models and mitigations through a use case on medical data.” HAL: 1–8. https://inria.hal.science/hal-04138528.

Harvard

Berthelier, G., Boutet, A. and Richard, A. (2023) ‘Privacy leakages on NLP models and mitigations through a use case on medical data’, HAL, pp. 1–8. Available at: https://inria.hal.science/hal-04138528.

IEEE

G. Berthelier, A. Boutet, and A. Richard, “Privacy leakages on NLP models and mitigations through a use case on medical data,” HAL, pp. 1–8, 2023.

BibTeX

@article{berthelier2023privacy,
  title     = {{Privacy leakages on NLP models and mitigations through a use case on medical data}},
  author    = {Berthelier, Gaspard and Boutet, Antoine and Richard, Antoine},
  journal   = {HAL},
  year      = {2023},
  pages     = {1--8},
  url       = {https://inria.hal.science/hal-04138528}
}

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
  • natural language processing models
  • privacy risks
  • patient data protection
  • Hospices Civils de Lyon

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?

Berthelier, G., Boutet, A., & Richard, A. (2023). Privacy leakages on NLP models and mitigations through a use case on medical data. HAL, 1–8. https://inria.hal.science/hal-04138528

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 HAL: sign in and open the PDF from this page.

Who wrote this paper?

Gaspard Berthelier, Antoine Boutet, Antoine Richard.

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.