Preprint · 2020 · Open access

Differentially Private Generation of Small Images

Justus T. C. Schwabedal, Michel, Pascal, Mario S. Riontino

arXiv (Cornell University) · Published 2 May 2020 · DOI 10.48550/arxiv.2005.00783

Open PDFView at the publisherCite this paper

In brief

“Differentially Private Generation of Small Images” is a 2020 preprint by Justus T. C. Schwabedal and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
3
Most cited in
2020 (1)
References
12
Authors
3

Abstract

We explore the training of generative adversarial networks with differential privacy to anonymize image data sets. On MNIST, we numerically measure the privacy-utility trade-off using parameters from $ε$-$δ$ differential privacy and the inception score. Our experiments uncover a saturated training regime where an increasing privacy budget adds little to the quality of generated images. We also explain analytically why differentially private Adam optimization is independent of the gradient clipping parameter. Furthermore, we highlight common errors in previous works on differentially private deep learning, which we uncovered in recent literature. Throughout the treatment of the subject, we hope to prevent erroneous estimates of anonymity in the future.

Cite this paper

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

APA 7

Schwabedal, J. T. C., Pascal, M., & Riontino, M. S. (2020). Differentially Private Generation of Small Images. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2005.00783

MLA 9

Schwabedal, Justus T. C., et al. “Differentially Private Generation of Small Images.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2005.00783.

Chicago

Schwabedal, Justus T. C., Michel, Pascal, and Mario S. Riontino. 2020. “Differentially Private Generation of Small Images.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2005.00783.

Harvard

Schwabedal, J. T. C., Pascal, M. and Riontino, M. S. (2020) ‘Differentially Private Generation of Small Images’, arXiv (Cornell University). doi:10.48550/arxiv.2005.00783.

IEEE

J. T. C. Schwabedal, M. Pascal, and M. S. Riontino, “Differentially Private Generation of Small Images,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2005.00783.

BibTeX

@misc{schwabedal2020differentially,
  title     = {{Differentially Private Generation of Small Images}},
  author    = {Schwabedal, Justus T. C. and Pascal, Michel, and Riontino, Mario S.},
  howpublished = {arXiv (Cornell University)},
  year      = {2020},
  doi       = {10.48550/arxiv.2005.00783},
  url       = {https://doi.org/10.48550/arxiv.2005.00783}
}

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

Citations by year

YearCitationsShare of the best year
202011
202211
202311

Topic and keywords

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

  • differential privacy
  • generative adversarial networks
  • image generation
  • privacy-utility trade-off
  • MNIST
  • Inception Score
  • Adam optimizer
  • gradient clipping

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?

Schwabedal, J. T. C., Pascal, M., & Riontino, M. S. (2020). Differentially Private Generation of Small Images. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2005.00783

How many times has this paper been cited?

3 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?

Justus T. C. Schwabedal, Michel, Pascal, Mario S. Riontino.

What is the DOI of this paper?

10.48550/arxiv.2005.00783, permanently at https://doi.org/10.48550/arxiv.2005.00783. 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.