Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis
This work addresses the need for privacy-preserving data analytics in regulated domains, offering a novel framework for secure data sharing.
The paper tackled the problem of generating synthetic tabular data with strong privacy guarantees by integrating differential privacy, federated learning, and diffusion models, achieving significant improvements in privacy without compromising data quality on multiple real-world datasets.
The increasing demand for privacy-preserving data analytics in various domains necessitates solutions for synthetic data generation that rigorously uphold privacy standards. We introduce the DP-FedTabDiff framework, a novel integration of Differential Privacy, Federated Learning and Denoising Diffusion Probabilistic Models designed to generate high-fidelity synthetic tabular data. This framework ensures compliance with privacy regulations while maintaining data utility. We demonstrate the effectiveness of DP-FedTabDiff on multiple real-world mixed-type tabular datasets, achieving significant improvements in privacy guarantees without compromising data quality. Our empirical evaluations reveal the optimal trade-offs between privacy budgets, client configurations, and federated optimization strategies. The results affirm the potential of DP-FedTabDiff to enable secure data sharing and analytics in highly regulated domains, paving the way for further advances in federated learning and privacy-preserving data synthesis.