Preprint · 2024 · Open access
DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
arXiv (Cornell University) · Published 21 March 2024 · DOI 10.48550/arxiv.2403.14421
In brief
“DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning” is a 2024 preprint by Jonathan Lebensold and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 9 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
- 9
- Most cited in
- 2026 (6)
- References
- 42
- Authors
- 7
Abstract
Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable. To remedy this issue, we develop the first differentially private (DP) retrieval-augmented generation algorithm that is capable of generating high-quality image samples while providing provable privacy guarantees. Specifically, we assume access to a text-to-image diffusion model trained on a small amount of public data, and design a DP retrieval mechanism to augment the text prompt with samples retrieved from a private retrieval dataset. Our \emph{differentially private retrieval-augmented diffusion model} (DP-RDM) requires no fine-tuning on the retrieval dataset to adapt to another domain, and can use state-of-the-art generative models to generate high-quality image samples while satisfying rigorous DP guarantees. For instance, when evaluated on MS-COCO, our DP-RDM can generate samples with a privacy budget of $ε=10$, while providing a $3.5$ point improvement in FID compared to public-only retrieval for up to $10,000$ queries.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lebensold, J., Sanjabi, M., Astolfi, P., Romero, A., Chaudhuri, K., Rabbat, M., & Guo, C. (2024). DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2403.14421
MLA 9
Lebensold, Jonathan, et al. “DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2403.14421.
Chicago
Lebensold, Jonathan, Maziar Sanjabi, Pietro Astolfi, Adriana Romero, Kamalika Chaudhuri, Mike Rabbat, and Chuan Guo. 2024. “DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2403.14421.
Harvard
Lebensold, J. et al. (2024) ‘DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning’, arXiv (Cornell University). doi:10.48550/arxiv.2403.14421.
IEEE
J. Lebensold et al., “DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2403.14421.
BibTeX
@misc{lebensold2024adapting,
title = {{DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning}},
author = {Lebensold, Jonathan and Sanjabi, Maziar and Astolfi, Pietro and Romero, Adriana and Chaudhuri, Kamalika and Rabbat, Mike and Guo, Chuan},
howpublished = {arXiv (Cornell University)},
year = {2024},
doi = {10.48550/arxiv.2403.14421},
url = {https://doi.org/10.48550/arxiv.2403.14421}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2023 | 1 | |
| 2025 | 2 | |
| 2026 | 6 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- text-to-image diffusion models
- differential privacy
- retrieval-augmented generation
- image generation
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?
Lebensold, J., Sanjabi, M., Astolfi, P., Romero, A., Chaudhuri, K., Rabbat, M., & Guo, C. (2024). DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2403.14421
How many times has this paper been cited?
9 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?
Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi, Adriana Romero, Kamalika Chaudhuri, Mike Rabbat, Chuan Guo.
What is the DOI of this paper?
10.48550/arxiv.2403.14421, permanently at https://doi.org/10.48550/arxiv.2403.14421. 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.