Preprint · 2026 · Open access

Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD

Qiwei Ma, Jun Zhang

arXiv (Cornell University) · Published 21 January 2026 · DOI 10.48550/arxiv.2601.15061

Open PDFView at the publisherCite this paper

In brief

“Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD” is a 2026 preprint by Qiwei Ma and Jun Zhang, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
21
Authors
2

Abstract

Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it generates a large number of training samples and prevents information leakage in real data. The existing methods suffer from the repeating trade-off processes between privacy and utility. We propose a novel framework for differential privacy generation, which employs an Error Feedback Stochastic Gradient Descent(EFSGD) method and introduces a reconstruction loss and noise injection mechanism into the training process. We generate images with higher quality and usability under the same privacy budget as the related work. Extensive experiments demonstrate the effectiveness and generalization of our proposed framework for both grayscale and RGB images. We achieve state-of-the-art results over almost all metrics on three benchmarks: MNIST, Fashion-MNIST, and CelebA.

Cite this paper

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

APA 7

Ma, Q., & Zhang, J. (2026). Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2601.15061

MLA 9

Ma, Qiwei, and Jun Zhang. “Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2601.15061.

Chicago

Ma, Qiwei and Jun Zhang. 2026. “Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2601.15061.

Harvard

Ma, Q. and Zhang, J. (2026) ‘Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD’, arXiv (Cornell University). doi:10.48550/arxiv.2601.15061.

IEEE

Q. Ma and J. Zhang, “Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2601.15061.

BibTeX

@misc{ma2026differential,
  title     = {{Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD}},
  author    = {Ma, Qiwei and Zhang, Jun},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2601.15061},
  url       = {https://doi.org/10.48550/arxiv.2601.15061}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • differential privacy
  • image generation
  • synthetic data
  • reconstruction loss
  • noise injection
  • privacy-utility trade-off
  • privacy-preserving machine learning
  • data masking

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?

Ma, Q., & Zhang, J. (2026). Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2601.15061

How many times has this paper been cited?

1 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?

Qiwei Ma, Jun Zhang.

What is the DOI of this paper?

10.48550/arxiv.2601.15061, permanently at https://doi.org/10.48550/arxiv.2601.15061. 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.