Preprint · 2021 · Open access

Benchmarking Differential Privacy and Federated Learning for BERT Models

Priyam Basu, Tiasa Singha Roy, Rakshit Naidu, Zümrüt Müftüoğlu, Sahib Singh, Fatemehsadat Mireshghallah

arXiv (Cornell University) · Published 26 June 2021 · DOI 10.48550/arxiv.2106.13973

Open PDFView at the publisherCite this paper

In brief

“Benchmarking Differential Privacy and Federated Learning for BERT Models” is a 2021 preprint by Priyam Basu and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 78 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
78
Most cited in
2023 (25)
References
39
Authors
6

Abstract

Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depression is a serious medical illness that can have adverse effects on how one feels, thinks, and acts, which can lead to emotional and physical problems. Due to the sensitive nature of such data, privacy measures need to be taken for handling and training models with such data. In this work, we study the effects that the application of Differential Privacy (DP) has, in both a centralized and a Federated Learning (FL) setup, on training contextualized language models (BERT, ALBERT, RoBERTa and DistilBERT). We offer insights on how to privately train NLP models and what architectures and setups provide more desirable privacy utility trade-offs. We envisage this work to be used in future healthcare and mental health studies to keep medical history private. Therefore, we provide an open-source implementation of this work.

Cite this paper

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

APA 7

Basu, P., Roy, T. S., Naidu, R., Müftüoğlu, Z., Singh, S., & Mireshghallah, F. (2021). Benchmarking Differential Privacy and Federated Learning for BERT Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2106.13973

MLA 9

Basu, Priyam, et al. “Benchmarking Differential Privacy and Federated Learning for BERT Models.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2106.13973.

Chicago

Basu, Priyam, Tiasa Singha Roy, Rakshit Naidu, Zümrüt Müftüoğlu, Sahib Singh, and Fatemehsadat Mireshghallah. 2021. “Benchmarking Differential Privacy and Federated Learning for BERT Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2106.13973.

Harvard

Basu, P. et al. (2021) ‘Benchmarking Differential Privacy and Federated Learning for BERT Models’, arXiv (Cornell University). doi:10.48550/arxiv.2106.13973.

IEEE

P. Basu, T. S. Roy, R. Naidu, Z. Müftüoğlu, S. Singh, and F. Mireshghallah, “Benchmarking Differential Privacy and Federated Learning for BERT Models,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2106.13973.

BibTeX

@misc{basu2021benchmarking,
  title     = {{Benchmarking Differential Privacy and Federated Learning for BERT Models}},
  author    = {Basu, Priyam and Roy, Tiasa Singha and Naidu, Rakshit and Müftüoğlu, Zümrüt and Singh, Sahib and Mireshghallah, Fatemehsadat},
  howpublished = {arXiv (Cornell University)},
  year      = {2021},
  doi       = {10.48550/arxiv.2106.13973},
  url       = {https://doi.org/10.48550/arxiv.2106.13973}
}

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

Citations by year

YearCitationsShare of the best year
202155
20221414
20232525
20241616
20251111
202677

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • differential privacy
  • federated learning
  • BERT
  • contextual language models
  • privacy-utility trade-off
  • depression diagnosis
  • ALBERT
  • RoBERTa

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?

Basu, P., Roy, T. S., Naidu, R., Müftüoğlu, Z., Singh, S., & Mireshghallah, F. (2021). Benchmarking Differential Privacy and Federated Learning for BERT Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2106.13973

How many times has this paper been cited?

78 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?

Priyam Basu, Tiasa Singha Roy, Rakshit Naidu, Zümrüt Müftüoğlu, Sahib Singh, Fatemehsadat Mireshghallah.

What is the DOI of this paper?

10.48550/arxiv.2106.13973, permanently at https://doi.org/10.48550/arxiv.2106.13973. 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.