mlsanityData to 14 Oct 2026

Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directions

arXiv 2311.17453 ↗First posted 29 Nov 2023cs.AI cs.CR cs.DBcited by 4

Not on the map. Why?

Abstract (arXiv)

Synthetic data (SD) have garnered attention as a privacy enhancing technology. Unfortunately, there is no standard for quantifying their degree of privacy protection. In this paper, we discuss proposed quantification approaches. This contributes to the development of SD privacy standards; stimulates multi-disciplinary discussion; and helps SD researchers make informed modeling and evaluation decisions.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 52 of its 122 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

52 of 122 references.

References · 52

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  6. 2019Modeling Tabular data using Conditional GANcited by 699
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  8. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  9. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  10. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  11. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  12. 2022Language Models are Realistic Tabular Data Generatorscited by 294
38 more
  1. 2018Differentially Private Generative Adversarial Networkcited by 235
  2. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  3. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  4. 2017Machine Learning Models that Remember Too Muchcited by 169
  5. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  6. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  7. 2020Adversarial Machine Learning -- Industry Perspectivescited by 122
  8. 2019Synthetic Data for Deep Learningcited by 113
  9. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 108
  10. 2021Winning the NIST Contest: A scalable and general approach to differentially private synthetic datacited by 102
  11. 2023REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformerscited by 94
  12. 2018Synthesizing Tabular Data using Generative Adversarial Networkscited by 92
  13. 2018IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesiscited by 85
  14. 2019Graphical-model based estimation and inference for differential privacycited by 74
  15. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 70
  16. 2022Synthetic Data -- what, why and how?cited by 67
  17. 2023Membership Inference Attacks against Synthetic Data through Overfitting Detectioncited by 66
  18. 2018On GANs and GMMscited by 62
  19. 2022TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Datacited by 57
  20. 2023Generative Table Pre-training Empowers Models for Tabular Predictioncited by 55
  21. 2022A Unified Framework for Quantifying Privacy Risk in Synthetic Datacited by 46
  22. 2020An Overview of Privacy in Machine Learningcited by 39
  23. 2020Differentially Private Synthetic Data: Applied Evaluations and Enhancementscited by 36
  24. 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
  25. 2023Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishingcited by 28
  26. 2020Attribute Privacy: Framework and Mechanismscited by 19
  27. 2023Synthesizing Mixed-type Electronic Health Records using Diffusion Modelscited by 18
  28. 2019Failure Modes in Machine Learning Systemscited by 15
  29. 2022Dissecting Distribution Inferencecited by 15
  30. 2022dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generationcited by 12
  31. 2023Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generationcited by 9
  32. 2020Hide-and-Seek Privacy Challengecited by 8
  33. 2021On Utility and Privacy in Synthetic Genomic Datacited by 8
  34. 2022Generating Realistic Synthetic Relational Data through Graph Variational Autoencoderscited by 8
  35. 2023Summary Statistic Privacy in Data Sharingcited by 6
  36. 2023Diverse Community Data for Benchmarking Data Privacy Algorithmscited by 6
  37. 2021Generation of Synthetic Electronic Health Records Using a Federated GANcited by 5
  38. 2021Effective and Privacy preserving Tabular Data Synthesizingcited by 2

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025A Consensus Privacy Metrics Framework for Synthetic Datacited by 8
  2. 2025Graph-Conditional Flow Matching for Relational Data Generationcited by 3
  3. 2025Contrastive Learning-Based privacy metrics in Tabular Synthetic Datasetscited by 2
  4. 2025Synthetic data for ratemaking: imputation-based methods vs adversarial networks and autoencoderscited by 0