Journal article · 2022 · Open access
Differentially Private Diffusion Models
Transactions on machine learning research · Published 18 October 2022 · DOI 10.48550/arxiv.2210.09929
In brief
“Differentially Private Diffusion Models” is a 2022 journal article by Tim Dockhorn and 3 co-authors, published in Transactions on machine learning research. OpenAlex counts 147 citations as of 19 November 2026, which puts it in the top 8% of works published in 2022 by citations. It is open access under a CC BY licence: the full text is free to read at Transactions on machine learning research.
- Citations
- 147
- Most cited in
- 2025 (48)
- Field-weighted impact
- 6.23
- References
- 81
- Authors
- 4
Abstract
While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge, providing access to synthetic data instead. We build on the recent success of diffusion models (DMs) and introduce Differentially Private Diffusion Models (DPDMs), which enforce privacy using differentially private stochastic gradient descent (DP-SGD). We investigate the DM parameterization and the sampling algorithm, which turn out to be crucial ingredients in DPDMs, and propose noise multiplicity, a powerful modification of DP-SGD tailored to the training of DMs. We validate our novel DPDMs on image generation benchmarks and achieve state-of-the-art performance in all experiments. Moreover, on standard benchmarks, classifiers trained on DPDM-generated synthetic data perform on par with task-specific DP-SGD-trained classifiers, which has not been demonstrated before for DP generative models. Project page and code: https://nv-tlabs.github.io/DPDM.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Dockhorn, T., Cao, T., Vahdat, A., & Kreis, K. (2022). Differentially Private Diffusion Models. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2210.09929
MLA 9
Dockhorn, Tim, et al. “Differentially Private Diffusion Models.” Transactions on machine learning research, 2022. https://doi.org/10.48550/arxiv.2210.09929.
Chicago
Dockhorn, Tim, Tianshi Cao, Arash Vahdat, and Karsten Kreis. 2022. “Differentially Private Diffusion Models.” Transactions on machine learning research. https://doi.org/10.48550/arxiv.2210.09929.
Harvard
Dockhorn, T. et al. (2022) ‘Differentially Private Diffusion Models’, Transactions on machine learning research. doi:10.48550/arxiv.2210.09929.
IEEE
T. Dockhorn, T. Cao, A. Vahdat, and K. Kreis, “Differentially Private Diffusion Models,” Transactions on machine learning research, 2022, doi: 10.48550/arxiv.2210.09929.
BibTeX
@article{dockhorn2022differentially,
title = {{Differentially Private Diffusion Models}},
author = {Dockhorn, Tim and Cao, Tianshi and Vahdat, Arash and Kreis, Karsten},
journal = {Transactions on machine learning research},
year = {2022},
doi = {10.48550/arxiv.2210.09929},
url = {https://doi.org/10.48550/arxiv.2210.09929}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 2 | |
| 2023 | 24 | |
| 2024 | 37 | |
| 2025 | 48 | |
| 2026 | 36 |
Its field-weighted citation impact is 6.23: it has been cited 6.23 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- differential privacy
- diffusion models
- DP-SGD
- generative models
- image generation
- synthetic data
- privacy-preserving training
- sampling algorithms
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?
Dockhorn, T., Cao, T., Vahdat, A., & Kreis, K. (2022). Differentially Private Diffusion Models. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2210.09929
How many times has this paper been cited?
147 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 Transactions on machine learning research: sign in and open the full text from this page.
Who wrote this paper?
Tim Dockhorn, Tianshi Cao, Arash Vahdat, Karsten Kreis.
What is the DOI of this paper?
10.48550/arxiv.2210.09929, permanently at https://doi.org/10.48550/arxiv.2210.09929. 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.