Journal article · 2025 · Open access
Differentially Private Image Classification by Learning Priors from Random Processes
Journal of Privacy and Confidentiality, 15(1) · Published 31 March 2025 · DOI 10.29012/jpc.910
In brief
“Differentially Private Image Classification by Learning Priors from Random Processes” is a 2025 journal article by Xinyu Tang and 3 co-authors, published in Journal of Privacy and Confidentiality. OpenAlex counts 9 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of Privacy and Confidentiality.
- Citations
- 9
- Most cited in
- 2025 (5)
- Field-weighted impact
- 0.95
- References
- 45
- Authors
- 4
Abstract
In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A recent focus in private learning research is improving the performance of DP-SGD on private data by incorporating priors that are learned on real-world public data. In this work, we explore how we can improve the privacy-utility tradeoff of DP-SGD by learning priors from images generated by random processes and transferring these priors to private data. We propose DP-RandP, a three-phase approach. We attain new state-of-the-art accuracy when training from scratch on CIFAR10, CIFAR100, MedMNIST and ImageNet for a range of privacy budgets $\epsilon \in [1, 8]$. In particular, we improve the previous best reported accuracy on CIFAR10 from $60.6 \%$ to $72.3 \%$ for $\epsilon=1$.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Tang, X., Panda, A., Sehwag, V., & Mittal, P. (2025). Differentially Private Image Classification by Learning Priors from Random Processes. Journal of Privacy and Confidentiality, 15(1). https://doi.org/10.29012/jpc.910
MLA 9
Tang, Xinyu, et al. “Differentially Private Image Classification by Learning Priors from Random Processes.” Journal of Privacy and Confidentiality, vol. 15, no. 1, 2025. https://doi.org/10.29012/jpc.910.
Chicago
Tang, Xinyu, Ashwinee Panda, Vikash Sehwag, and Prateek Mittal. 2025. “Differentially Private Image Classification by Learning Priors from Random Processes.” Journal of Privacy and Confidentiality 15 (1). https://doi.org/10.29012/jpc.910.
Harvard
Tang, X. et al. (2025) ‘Differentially Private Image Classification by Learning Priors from Random Processes’, Journal of Privacy and Confidentiality, 15(1). doi:10.29012/jpc.910.
IEEE
X. Tang, A. Panda, V. Sehwag, and P. Mittal, “Differentially Private Image Classification by Learning Priors from Random Processes,” Journal of Privacy and Confidentiality, vol. 15, no. 1, 2025, doi: 10.29012/jpc.910.
BibTeX
@article{tang2025differentially,
title = {{Differentially Private Image Classification by Learning Priors from Random Processes}},
author = {Tang, Xinyu and Panda, Ashwinee and Sehwag, Vikash and Mittal, Prateek},
journal = {Journal of Privacy and Confidentiality},
year = {2025},
volume = {15},
number = {1},
doi = {10.29012/jpc.910},
url = {https://doi.org/10.29012/jpc.910}
}
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 | |
| 2024 | 3 | |
| 2025 | 5 |
Its field-weighted citation impact is 0.95: it has been cited 0.95 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
- image classification
- DP-SGD
- learned priors
- privacy-utility trade-off
- privacy-preserving machine learning
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?
Tang, X., Panda, A., Sehwag, V., & Mittal, P. (2025). Differentially Private Image Classification by Learning Priors from Random Processes. Journal of Privacy and Confidentiality, 15(1). https://doi.org/10.29012/jpc.910
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 Journal of Privacy and Confidentiality: sign in and open the full text from this page.
Who wrote this paper?
Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal.
What is the DOI of this paper?
10.29012/jpc.910, permanently at https://doi.org/10.29012/jpc.910. 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.