mlsanityData to 14 Oct 2026

TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data

arXiv 2211.06550 ↗First posted 12 Nov 2022cs.CR cs.AI cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Personal data collected at scale promises to improve decision-making and accelerate innovation. However, sharing and using such data raises serious privacy concerns. A promising solution is to produce synthetic data, artificial records to share instead of real data. Since synthetic records are not linked to real persons, this intuitively prevents classical re-identification attacks. However, this is insufficient to protect privacy. We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios. These attacks include generalizations of prior works and novel attacks. We also introduce a general framework for reasoning about privacy threats to synthetic data and showcase TAPAS on several examples.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). Builds on 9 of its 22 references that are in the map. First posted on arXiv 12 Nov 2022.

Builds on

9 of 22 references.

References · 9

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  2. 2019Modeling Tabular data using Conditional GANcited by 699
  3. 2013The Composition Theorem for Differential Privacycited by 297
  4. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 218
  5. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
  6. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 108
  7. 2019Graphical-model based estimation and inference for differential privacycited by 74
  8. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 70
  9. 2022Bayesian Estimation of Differential Privacycited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 14; 2025: 16; 2026: 16.

57 papers.

Sort:

By area:

  1. 2023Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishingcited by 28
  2. 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Datacited by 24
  3. 2023Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic datacited by 18
  4. 2024Systematic Assessment of Tabular Data Synthesiscited by 18
  5. 2025The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Textcited by 18
  6. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
  7. 2023Auditing and Generating Synthetic Data with Controllable Trust Trade-offscited by 13
  8. 2023Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utilitycited by 13
  9. 2024The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debuggingcited by 13
  10. 2024Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Modelscited by 12
  11. 2025The DCR Delusion: Measuring the Privacy Risk of Synthetic Datacited by 11
  12. 2024SiloFuse: Cross-silo Synthetic Data Generation with Latent Tabular Diffusion Modelscited by 10
38 more
  1. 2024Privacy Vulnerabilities in Marginals-based Synthetic Datacited by 10
  2. 2023Investigating the Effect of Misalignment on Membership Privacy in the White-box Settingcited by 9
  3. 2025Synthetic Tabular Data: Methods, Attacks and Defensescited by 9
  4. 2025Synthetic Data Privacy Metricscited by 8
  5. 2025A Consensus Privacy Metrics Framework for Synthetic Datacited by 8
  6. 2023FLAIM: AIM-based Synthetic Data Generation in the Federated Settingcited by 6
  7. 2024Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Datacited by 6
  8. 2024DP-TLDM: Differentially Private Tabular Latent Diffusion Modelcited by 5
  9. 2025The Importance of Being Discrete: Measuring the Impact of Discretization in End-to-End Differentially Private Synthetic Datacited by 5
  10. 2025The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditingcited by 5
  11. 2025Privacy Auditing Synthetic Data Release through Local Likelihood Attackscited by 5
  12. 2023A Unified View of Differentially Private Deep Generative Modelingcited by 4
  13. 2023Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directionscited by 4
  14. 2024A Zero Auxiliary Knowledge Membership Inference Attack on Aggregate Location Datacited by 4
  15. 2025Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Aheadcited by 4
  16. 2025Ensembling Membership Inference Attacks Against Tabular Generative Modelscited by 4
  17. 2025Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesiscited by 4
  18. 2024Synthetic Data Outliers: Navigating Identity Disclosurecited by 3
  19. 2025When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generationcited by 3
  20. 2025Contrastive Learning-Based privacy metrics in Tabular Synthetic Datasetscited by 2
  21. 2026Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Settingcited by 2
  22. 2026Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing (Extended Version)cited by 2
  23. 2023On the Challenges of Deploying Privacy-Preserving Synthetic Data in the Enterprisecited by 1
  24. 2024Six Levels of Privacy: A Framework for Financial Synthetic Datacited by 1
  25. 2024VFLGAN: Vertical Federated Learning-based Generative Adversarial Network for Vertically Partitioned Data Publicationcited by 1
  26. 2024Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliancecited by 1
  27. 2025Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distancecited by 1
  28. 2026Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspectivecited by 1
  29. 2026ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learningcited by 1
  30. 2026Tight Auditing of Differential Privacy in MST and AIMcited by 1
  31. 2026A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilitiescited by 1
  32. 2024Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Modelscited by 0
  33. 2024Automated Privacy-Preserving Techniques via Meta-Learningcited by 0
  34. 2025DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statisticscited by 0
  35. 2025Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGNcited by 0
  36. 2026Privacy Amplification Persists under Unlimited Synthetic Data Releasecited by 0
  37. 2026diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectoriescited by 0
  38. 2026ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generatorscited by 0

50 most cited of 57 All 57 (JSON)