mlsanityData to 14 Oct 2026

Membership Inference over Diffusion-models-based Synthetic Tabular Data

arXiv 2510.16037 ↗First posted 16 Oct 2025cs.CR cs.AI cs.LGcited by 2

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn, by developing query-based MIAs based on the step-wise error comparison method. Our findings reveal that TabDDPM is more vulnerable to these attacks. TabSyn exhibits resilience against our attack models. Our work underscores the importance of evaluating the privacy implications of diffusion models and encourages further research into robust privacy-preserving mechanisms for synthetic data generation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 10 of its 18 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

10 of 18 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?2 Feb

Other references · 9

  1. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2021Membership Inference Attacks From First Principlescited by 878
  4. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  5. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  6. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  7. 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 70
  8. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  9. 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metricscited by 0
  2. 2026Position: Privacy Is a Claim, Not a Property of Synthetic Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
  2. 2025Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
  3. 2026Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Setting
  4. 2025Ensembling Membership Inference Attacks Against Tabular Generative Models
  5. 2025Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis
  6. 2026Differentially Private Synthetic Data via APIs 4: Tabular Data
  7. 2024Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis
  8. 2024DP-TLDM: Differentially Private Tabular Latent Diffusion Model