mlsanityData to 13 Oct 2026

Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano

arXiv 2210.13662 ↗First posted 24 Oct 2022cs.LG cs.CR cs.ITcited by 16

Not on the map. Why?

Abstract (arXiv)

Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy risks in machine learning. However, exactly how small the privacy parameter ε needs to be to protect against certain privacy risks in practice is still not well-understood. In this work, we study data reconstruction attacks for discrete data and analyze it under the framework of multiple hypothesis testing. We utilize different variants of the celebrated Fano's inequality to derive upper bounds on the inferential power of a data reconstruction adversary when the model is trained differentially privately. Importantly, we show that if the underlying private data takes values from a set of size M, then the target privacy parameter ε can be O(log M) before the adversary gains significant inferential power. Our analysis offers theoretical evidence for the empirical effectiveness of DP against data reconstruction attacks even at relatively large values of ε.

Key facts. Cited by 16 papers in the map (data through 13 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

27 of 55 references.

References · 27

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  2. 2016Deep Learning with Differential Privacycited by 2,718
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,273
  4. 2020Extracting Training Data from Large Language Modelscited by 2,181
  5. 2019Deep Leakage from Gradientscited by 1,017
  6. 2021Membership Inference Attacks From First Principlescited by 872
  7. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 711
  9. 2017Renyi Differential Privacycited by 648
  10. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 497
  11. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 456
  12. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 270
15 more
  1. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 247
  2. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 218
  3. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
  4. 2017Machine Learning Models that Remember Too Muchcited by 169
  5. 2022Reconstructing Training Data with Informed Adversariescited by 147
  6. 2021On the Importance of Difficulty Calibration in Membership Inference Attackscited by 144
  7. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 129
  8. 2020Improving Robustness to Model Inversion Attacks via Mutual Information Regularizationcited by 52
  9. 2022Bounding Training Data Reconstruction in Private (Deep) Learningcited by 45
  10. 2016Differential Privacy as a Mutual Information Constraintcited by 44
  11. 2021Measuring Data Leakage in Machine-Learning Models with Fisher Informationcited by 32
  12. 2022Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanismscited by 19
  13. 2019That which we call privatecited by 16
  14. 2022Bounding Membership Inferencecited by 15
  15. 2017On w-mixtures: Finite convex combinations of prescribed component distributionscited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 10; 2024: 3; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 151
  2. 2023Bounding Training Data Reconstruction in DP-SGDcited by 45
  3. 2023One-shot Empirical Privacy Estimation for Federated Learningcited by 36
  4. 2023Unlocking Accuracy and Fairness in Differentially Private Image Classificationcited by 16
  5. 2023Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacycited by 14
  6. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
  7. 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacycited by 13
  8. 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Informationcited by 12
  9. 2023Information Flow Control in Machine Learning through Modular Model Architecturecited by 11
  10. 2023Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networkscited by 10
  11. 2023Fundamental Limits of Membership Inference Attacks on Machine Learning Modelscited by 5
  12. 2024Differentially Private Representation Learning via Image Captioningcited by 5
4 more
  1. 2024Analyzing Inference Privacy Risks Through Gradients in Machine Learningcited by 4
  2. 2024Implicit Bias in Noisy-SGD: With Applications to Differentially Private Trainingcited by 2
  3. 2025Cocoon: A System Architecture for Differentially Private Training with Correlated Noisescited by 1
  4. 2026A Sharp Transition in Data Reconstruction under Differential Privacycited by 0