Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Tabular Data GenerationSimilar Papers 제목 키워드 기반
FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation
Realistic synthetic tabular data generation encounters significant challenges in preserving privacy, especially when dealing with sensitive information in domains like finance and healthcare. In this paper, we introduce …
AttributeDenoisingFederated LearningTabular Data GenerationMIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative models like diffusion models, synthetic data is expected to preserve the s…
Measuring Privacy Risks and Tradeoffs in Financial Synthetic Data Generation
We explore the privacy-utility tradeoff of synthetic data generation schemes on tabular financial datasets, a domain characterized by high regulatory risk and severe class imbalance. We consider representative tabular da…
Synthetic Data GenerationAutoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data
Synthetic data generation is an important capability for privacy-preserving data sharing, system benchmarking and test data provisioning. For mixed-type data, existing synthesizers largely target dense, fixed-schema tabl…
Synthetic Data GenerationGenerating tabular datasets under differential privacy
Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessible and high-quality training data. Some of the most important datasets are found in biomedical and financial domains in t…
Synthetic Data Generation