On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
cs.LG, cs.AI
Submitted: 2026-05-07
Updated: 2026-09-25
Code: https://github.com/VectorInstitute/midst-toolkit
Terminology
Sources
- Membership Inference over Diffusion-models-based Synthetic Tabular Data
- MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
- SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data
- Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
- Efficacy of Synthetic Data as a Benchmark
- MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
- Synthetic Data Privacy Metrics
- Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
- DP-TLDM: Differentially Private Tabular Latent Diffusion Model
- That which we call private
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