Journal article · 2023 · Open access

DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation

Dihong Jiang, Sun Sun

Transactions on machine learning research · Published 1 November 2023

Open full textCite this paper

In brief

“DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation” is a 2023 journal article by Dihong Jiang and Sun Sun, published in Transactions on machine learning research. OpenAlex counts 6 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Transactions on machine learning research.

Citations
6
Most cited in
2025 (3)
Field-weighted impact
0.34
References
39
Authors
2

Abstract

Privacy concerns grow with the success of modern deep learning models, especially when the training set contains sensitive data. Differentially private generative model (DPGM) can serve as a solution to circumvent such concerns by generating data that are distributionally similar to the original data yet with differential privacy (DP) guarantees. While GAN has attracted major attention, existing DPGMs based on flow generative models are limited and only developed on low-dimensional tabular datasets. The capability of exact density estimation makes the flow model exceptional when density estimation is of interest. In this work, we will first show that it is challenging (or even infeasible) to train a DP-flow via DPSGD, i.e. the workhorse algorithm for private deep learning, on high-dimensional image sets with acceptable utility, and then we give an effective solution by reducing the generation from the pixel space to a lower dimensional latent space. We show the effectiveness and scalability of the proposed method via extensive experiments, where the proposed method achieves a significantly better privacy-utility trade-off compared to existing alternatives. Notably, our method is the first DPGM to scale to high-resolution image sets (up to 256 × 256).

Cite this paper

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

APA 7

Jiang, D., & Sun, S. (2023). DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation. Transactions on machine learning research. https://openreview.net/forum?id=GEcneTl9Mk

MLA 9

Jiang, Dihong, and Sun Sun. “DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation.” Transactions on machine learning research, 2023. https://openreview.net/forum?id=GEcneTl9Mk.

Chicago

Jiang, Dihong and Sun Sun. 2023. “DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation.” Transactions on machine learning research. https://openreview.net/forum?id=GEcneTl9Mk.

Harvard

Jiang, D. and Sun, S. (2023) ‘DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation’, Transactions on machine learning research. Available at: https://openreview.net/forum?id=GEcneTl9Mk.

IEEE

D. Jiang and S. Sun, “DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation,” Transactions on machine learning research, 2023.

BibTeX

@article{jiang2023lflow,
  title     = {{DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation}},
  author    = {Jiang, Dihong and Sun, Sun},
  journal   = {Transactions on machine learning research},
  year      = {2023},
  url       = {https://openreview.net/forum?id=GEcneTl9Mk}
}

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

Citations by year

YearCitationsShare of the best year
202311
202533
202622

Its field-weighted citation impact is 0.34: it has been cited 0.34 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
  • flow-based generative models
  • image generation
  • privacy-utility trade-off
  • high-dimensional data
  • privacy-preserving deep learning
  • DP-SGD
  • high-resolution imagery

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?

Jiang, D., & Sun, S. (2023). DP-LFlow: Differentially Private Latent Flow for Scalable Sensitive Image Generation. Transactions on machine learning research. https://openreview.net/forum?id=GEcneTl9Mk

How many times has this paper been cited?

6 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?

Dihong Jiang, Sun Sun.

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.