Journal article · 2023 · Open access

DP-LDMs: Differentially Private Latent Diffusion Models

Liu, Michael F., Saiyue Lyu, Margarita Vinaroz, Mijung Park

Transactions on machine learning research · Published 25 May 2023 · DOI 10.48550/arxiv.2305.15759

Open full textView at the publisherCite this paper

In brief

“DP-LDMs: Differentially Private Latent Diffusion Models” is a 2023 journal article by Liu, Michael F. and 3 co-authors, published in Transactions on machine learning research. OpenAlex counts 46 citations as of 19 November 2026, which puts it in the top 3% of works published in 2023 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
46
Most cited in
2025 (15)
Field-weighted impact
2.58
References
43
Authors
4

Abstract

Diffusion models (DMs) are one of the most widely used generative models for producing high quality images. However, a flurry of recent papers points out that DMs are least private forms of image generators, by extracting a significant number of near-identical replicas of training images from DMs. Existing privacy-enhancing techniques for DMs, unfortunately, do not provide a good privacy-utility tradeoff. In this paper, we aim to improve the current state of DMs with differential privacy (DP) by adopting the $\textit{Latent}$ Diffusion Models (LDMs). LDMs are equipped with powerful pre-trained autoencoders that map the high-dimensional pixels into lower-dimensional latent representations, in which DMs are trained, yielding a more efficient and fast training of DMs. Rather than fine-tuning the entire LDMs, we fine-tune only the $\textit{attention}$ modules of LDMs with DP-SGD, reducing the number of trainable parameters by roughly $90\%$ and achieving a better privacy-accuracy trade-off. Our approach allows us to generate realistic, high-dimensional images (256x256) conditioned on text prompts with DP guarantees, which, to the best of our knowledge, has not been attempted before. Our approach provides a promising direction for training more powerful, yet training-efficient differentially private DMs, producing high-quality DP images. Our code is available at https://anonymous.4open.science/r/DP-LDM-4525.

Cite this paper

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

APA 7

F., L. M., Lyu, S., Vinaroz, M., & Park, M. (2023). DP-LDMs: Differentially Private Latent Diffusion Models. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2305.15759

MLA 9

F., Liu, Michael, et al. “DP-LDMs: Differentially Private Latent Diffusion Models.” Transactions on machine learning research, 2023. https://doi.org/10.48550/arxiv.2305.15759.

Chicago

F., Liu, Michael, Saiyue Lyu, Margarita Vinaroz, and Mijung Park. 2023. “DP-LDMs: Differentially Private Latent Diffusion Models.” Transactions on machine learning research. https://doi.org/10.48550/arxiv.2305.15759.

Harvard

F., L. M. et al. (2023) ‘DP-LDMs: Differentially Private Latent Diffusion Models’, Transactions on machine learning research. doi:10.48550/arxiv.2305.15759.

IEEE

L. M. F., S. Lyu, M. Vinaroz, and M. Park, “DP-LDMs: Differentially Private Latent Diffusion Models,” Transactions on machine learning research, 2023, doi: 10.48550/arxiv.2305.15759.

BibTeX

@article{f2023ldms,
  title     = {{DP-LDMs: Differentially Private Latent Diffusion Models}},
  author    = {F., Liu, Michael and Lyu, Saiyue and Vinaroz, Margarita and Park, Mijung},
  journal   = {Transactions on machine learning research},
  year      = {2023},
  doi       = {10.48550/arxiv.2305.15759},
  url       = {https://doi.org/10.48550/arxiv.2305.15759}
}

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

Citations by year

YearCitationsShare of the best year
202355
20241414
20251515
20261212

Its field-weighted citation impact is 2.58: it has been cited 2.58 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
  • latent diffusion models
  • DP-SGD
  • privacy-utility trade-off
  • image generation
  • training efficiency
  • text-to-image generation

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?

F., L. M., Lyu, S., Vinaroz, M., & Park, M. (2023). DP-LDMs: Differentially Private Latent Diffusion Models. Transactions on machine learning research. https://doi.org/10.48550/arxiv.2305.15759

How many times has this paper been cited?

46 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?

Liu, Michael F., Saiyue Lyu, Margarita Vinaroz, Mijung Park.

What is the DOI of this paper?

10.48550/arxiv.2305.15759, permanently at https://doi.org/10.48550/arxiv.2305.15759. 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.