MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
On the map: Diffusion models → Robustness, privacy and adversarial aspects
also in 1 more
Abstract (arXiv)
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 statistical properties of the original dataset while remaining resilient to privacy attacks. Recent developments of diffusion models have been effective on a wide range of data types, but their privacy resilience, particularly for tabular formats, remains largely unexplored. MIDST challenge sought a quantitative evaluation of the privacy gain of synthetic tabular data generated by diffusion models, with a specific focus on its resistance to membership inference attacks (MIAs). Given the heterogeneity and complexity of tabular data, multiple target models were explored for MIAs, including diffusion models for single tables of mixed data types and multi-relational tables with interconnected constraints. MIDST inspired the development of novel black-box and white-box MIAs tailored to these target diffusion models as a key outcome, enabling a comprehensive evaluation of their privacy efficacy. The MIDST GitHub repository is available at https://github.com/VectorInstitute/MIDST
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 18 of its 27 references that are in the map. First posted on arXiv 19 Mar 2026.
Builds on
18 of 27 references.
Closest ancestors · 5
Same direction, newest first
- 2025MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data16 Sep
- 2025Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis15 Mar
- 2023White-box Membership Inference Attacks against Diffusion Models11 Aug
- 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?2 Feb
- 2023Extracting Training Data from Diffusion Models30 Jan
Other references · 13
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
- 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 183
- 2020Synthetic Data -- Anonymisation Groundhog Daycited by 105
- 2022STaSy: Score-based Tabular data Synthesiscited by 85
- 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesiscited by 78
- 2022Diffusion models for missing value imputation in tabular datacited by 77
- 2023Membership Inference Attacks against Synthetic Data through Overfitting Detectioncited by 66
- 2022A Unified Framework for Quantifying Privacy Risk in Synthetic Datacited by 45
- 2023Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Datacited by 31
- 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
- 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28
1 more
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Membership Inference over Diffusion-models-based Synthetic Tabular Data
- 2025Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
- 2023Membership Inference of Diffusion Models
- 2025Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation
- 2025The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
- 2025Flow Matching for Tabular Data Synthesis
- 2026Differentially Private Synthetic Data via APIs 4: Tabular Data
- 2024FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation