Journal article · 2023 · Open access

Differentially Private Denoise Diffusion Probability Models

Zhiguang Chu, Jingsha He, Dongdong Peng, Xing Zhang, Nafei Zhu

IEEE Access, 11, 108033–108040 · Published 1 January 2023 · DOI 10.1109/access.2023.3315592

Open PDFView at the publisherCite this paper

In brief

“Differentially Private Denoise Diffusion Probability Models” is a 2023 journal article by Zhiguang Chu and 4 co-authors, published in IEEE Access. OpenAlex counts 7 citations as of 19 November 2026, which puts it in the top 9% of works published in 2023 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at IEEE Access.

Citations
7
Most cited in
2024 (3)
Field-weighted impact
0.42
References
32
Authors
5

Abstract

Diffusion models and their variants have achieved high-quality image generation without adversarial training. These algorithms provide new ideas for data shortages in some fields. But the diffusion model also faces the same problem as other generative models: the learned probability density function will retain the characteristics of the training samples, which means that the high complexity of the deep network will make the model easily remember the training samples. When a diffusion model is applied to sensitive datasets, the distribution the model focuses on may reveal private information, and the security concerns described above become more pronounced. To address this challenge, this paper proposes a privacy diffusion model named DPDM (Differentially Private Denoise Diffusion Probability Models) that satisfies differential privacy by adding appropriate noise to the gradient during the training. Besides, this paper adopts a series of optimization strategies to improve model performance and training speed such as adaptive gradient clipping threshold and dynamic decay learning rate. Through the evaluation and analysis of the benchmark dataset, it is found that the attempt in this paper has promising usability, and the synthetic data has better performance.

Cite this paper

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

APA 7

Chu, Z., He, J., Peng, D., Zhang, X., & Zhu, N. (2023). Differentially Private Denoise Diffusion Probability Models. IEEE Access, 11, 108033–108040. https://doi.org/10.1109/access.2023.3315592

MLA 9

Chu, Zhiguang, et al. “Differentially Private Denoise Diffusion Probability Models.” IEEE Access, vol. 11, 2023, pp. 108033–108040. https://doi.org/10.1109/access.2023.3315592.

Chicago

Chu, Zhiguang, Jingsha He, Dongdong Peng, Xing Zhang, and Nafei Zhu. 2023. “Differentially Private Denoise Diffusion Probability Models.” IEEE Access 11: 108033–108040. https://doi.org/10.1109/access.2023.3315592.

Harvard

Chu, Z. et al. (2023) ‘Differentially Private Denoise Diffusion Probability Models’, IEEE Access, 11, pp. 108033–108040. doi:10.1109/access.2023.3315592.

IEEE

Z. Chu, J. He, D. Peng, X. Zhang, and N. Zhu, “Differentially Private Denoise Diffusion Probability Models,” IEEE Access, vol. 11, pp. 108033–108040, 2023, doi: 10.1109/access.2023.3315592.

BibTeX

@article{chu2023differentially,
  title     = {{Differentially Private Denoise Diffusion Probability Models}},
  author    = {Chu, Zhiguang and He, Jingsha and Peng, Dongdong and Zhang, Xing and Zhu, Nafei},
  journal   = {IEEE Access},
  year      = {2023},
  volume    = {11},
  pages     = {108033--108040},
  doi       = {10.1109/access.2023.3315592},
  url       = {https://doi.org/10.1109/access.2023.3315592}
}

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

Citations by year

YearCitationsShare of the best year
202311
202433
202522
202611

Its field-weighted citation impact is 0.42: it has been cited 0.42 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
  • synthetic data 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?

Chu, Z., He, J., Peng, D., Zhang, X., & Zhu, N. (2023). Differentially Private Denoise Diffusion Probability Models. IEEE Access, 11, 108033–108040. https://doi.org/10.1109/access.2023.3315592

How many times has this paper been cited?

7 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 IEEE Access: sign in and open the PDF from this page.

Who wrote this paper?

Zhiguang Chu, Jingsha He, Dongdong Peng, Xing Zhang, Nafei Zhu.

What is the DOI of this paper?

10.1109/access.2023.3315592, permanently at https://doi.org/10.1109/access.2023.3315592. 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.