# Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation

arXiv: https://arxiv.org/abs/2512.00638 · HTML: https://mlsanity.com/paper/2512.00638/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 29 of 29)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Numerical Composition of Differential Privacy](https://mlsanity.com/paper/2106.02848/) (2021)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis](https://mlsanity.com/paper/2304.12654/) (2023)
- [Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning](https://mlsanity.com/paper/2008.09202/) (2020)
- [Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications](https://mlsanity.com/paper/2010.05867/) (2020)
- [A Unified Framework for Quantifying Privacy Risk in Synthetic Data](https://mlsanity.com/paper/2211.10459/) (2022)
- [FinDiff: Diffusion Models for Financial Tabular Data Generation](https://mlsanity.com/paper/2309.01472/) (2023)
- [AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing](https://mlsanity.com/paper/2310.15479/) (2023)
- [On the Privacy Properties of GAN-generated Samples](https://mlsanity.com/paper/2206.01349/) (2022)
- [Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions](https://mlsanity.com/paper/1909.13403/) (2019)
- [Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits](https://mlsanity.com/paper/2208.12708/) (2022)
- [Diffusion and Flow Matching Models for Tabular Data: A Survey](https://mlsanity.com/paper/2502.17119/) (2025)
- [PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning](https://mlsanity.com/paper/2010.02529/) (2020)
- [DTGAN: Differential Private Training for Tabular GANs](https://mlsanity.com/paper/2107.02521/) (2021)
- [Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis](https://mlsanity.com/paper/2307.15424/) (2023)
- [Generating tabular datasets under differential privacy](https://mlsanity.com/paper/2308.14784/) (2023)

## Abstract (arXiv)

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.