Preprint · 2025 · Open access
Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation
arXiv (Cornell University) · Published 29 November 2025 · DOI 10.48550/arxiv.2512.00638
In brief
“Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation” is a 2025 preprint by Timur Sattarov and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2026 (2)
- References
- 32
- Authors
- 3
Abstract
We introduce DP-FinDiff, a differentially private diffusion framework for synthesizing mixed-type tabular data. DP-FinDiff employs embedding-based representations for categorical features, reducing encoding overhead and scaling to high-dimensional datasets. To adapt DP-training to the diffusion process, we propose two privacy-aware training strategies: an adaptive timestep sampler that aligns updates with diffusion dynamics, and a feature-aggregated loss that mitigates clipping-induced bias. Together, these enhancements improve fidelity and downstream utility without weakening privacy guarantees. On financial and medical datasets, DP-FinDiff achieves 16-42% higher utility than DP baselines at comparable privacy levels, demonstrating its promise for safe and effective data sharing in sensitive domains.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Sattarov, T., Schreyer, M., & Borth, D. (2025). Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.00638
MLA 9
Sattarov, Timur, et al. “Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2512.00638.
Chicago
Sattarov, Timur, Marco Schreyer, and Damian Borth. 2025. “Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.00638.
Harvard
Sattarov, T., Schreyer, M. and Borth, D. (2025) ‘Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation’, arXiv (Cornell University). doi:10.48550/arxiv.2512.00638.
IEEE
T. Sattarov, M. Schreyer, and D. Borth, “Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2512.00638.
BibTeX
@misc{sattarov2025privacy,
title = {{Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation}},
author = {Sattarov, Timur and Schreyer, Marco and Borth, Damian},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2512.00638},
url = {https://doi.org/10.48550/arxiv.2512.00638}
}
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
- diffusion models
- tabular data generation
- synthetic data
- mixed data
- privacy-preserving training
- financial data
- health data
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?
Sattarov, T., Schreyer, M., & Borth, D. (2025). Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.00638
How many times has this paper been cited?
3 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?
Timur Sattarov, Marco Schreyer, Damian Borth.
What is the DOI of this paper?
10.48550/arxiv.2512.00638, permanently at https://doi.org/10.48550/arxiv.2512.00638. 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.