Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis
cs.LG, cs.CR
Submitted: 2025-11-17
Updated: 2026-09-09
Comments: 18 pages. Github Link provided: https://github.com/KaiChen9909/margnet
Code: https://github.com/KaiChen9909/margnet
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation
- DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
- Providing Access to Confidential Research Data Through Synthesis and Verification: An Application to Data on Employees of the U.S. Federal Government
- Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
- AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data
- Differentially Private Releasing via Deep Generative Model (Technical Report)
- Privately generating tabular data using language models
- Benchmarking Differentially Private Tabular Data Synthesis
- Modeling Tabular data using Conditional GAN
- Winning the NIST Contest: A scalable and general approach to differentially private synthetic data
- GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
- Privacy Odometers and Filters: Pay-as-you-Go Composition
- Bounding, Concentrating, and Truncating: Unifying Privacy Loss Composition for Data Analytics
- Individual Privacy Accounting via a Renyi Filter
- Differentially Private Generative Adversarial Network
- Differentially Private Tabular Data Synthesis using Large Language Models
- New Oracle-Efficient Algorithms for Private Synthetic Data Release
- Systematic Assessment of Tabular Data Synthesis
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks