mlsanityData to 7 Oct 2026

Tight Auditing of Differential Privacy in MST and AIM

arXiv 2604.18352 ↗First posted 20 Apr 2026cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy (GDP)-based auditing framework that measures privacy via the full false-positive/false-negative tradeoff. Applied to MST and AIM under worst-case settings, our method provides the first tight audits in the strong-privacy regime. For (ε,δ)=(1,10-2), we obtain μemp≈0.43 vs. implied μ=0.45, showing a small theory-practice gap. Our code is publicly available: https://github.com/sassoftware/dpmm.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 20 Apr 2026.

Builds on

26 of 37 references.

References · 26

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  4. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  5. 2020The Discrete Gaussian for Differential Privacycited by 134
  6. 2023Privacy Auditing with One (1) Training Runcited by 119
  7. 2021Winning the NIST Contest: A scalable and general approach to differentially private synthetic datacited by 101
  8. 2022AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Datacited by 88
  9. 2021Benchmarking Differentially Private Synthetic Data Generation Algorithmscited by 80
  10. 2019Graphical-model based estimation and inference for differential privacycited by 73
  11. 2022TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Datacited by 56
  12. 2021Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Datacited by 48
14 more
  1. 2022Bayesian Estimation of Differential Privacycited by 31
  2. 2020Three Variants of Differential Privacy: Lossless Conversion and Applicationscited by 25
  3. 2024"What do you want from theory alone?" Experimenting with Tight Auditing of Differentially Private Synthetic Data Generationcited by 20
  4. 2023Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utilitycited by 13
  5. 2025Benchmarking Differentially Private Tabular Data Synthesiscited by 13
  6. 2024The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debuggingcited by 12
  7. 2023Synthetic Data: Methods, Use Cases, and Riskscited by 10
  8. 2022Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix Itcited by 8
  9. 2022Precision-based attacks and interval refining: how to break, then fix, differential privacy on finite computerscited by 8
  10. 2025Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learningcited by 6
  11. 2025The Importance of Being Discrete: Measuring the Impact of Discretization in End-to-End Differentially Private Synthetic Datacited by 4
  12. 2025The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditingcited by 4
  13. 2025dpmm: Differentially Private Marginal Models, a Library for Synthetic Tabular Data Generationcited by 2
  14. 2026Optimal conversion from R'enyi Differential Privacy to f-Differential Privacycited by 1

Built on by

Not cited yet.