mlsanityData to 7 Oct 2026

Hypothesis Testing Interpretations and Renyi Differential Privacy

arXiv 1905.09982 ↗First posted 24 May 2019cs.LG stat.MLcited by 84

Not on the map. Why?

Abstract (arXiv)

Differential privacy is a de facto standard in data privacy, with applications in the public and private sectors. A way to explain differential privacy, which is particularly appealing to statistician and social scientists is by means of its statistical hypothesis testing interpretation. Informally, one cannot effectively test whether a specific individual has contributed her data by observing the output of a private mechanism---any test cannot have both high significance and high power. In this paper, we identify some conditions under which a privacy definition given in terms of a statistical divergence satisfies a similar interpretation. These conditions are useful to analyze the distinguishability power of divergences and we use them to study the hypothesis testing interpretation of some relaxations of differential privacy based on Renyi divergence. This analysis also results in an improved conversion rule between these definitions and differential privacy.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 19; 2024: 17; 2025: 16; 2026: 9.

84 papers.

Sort:

By area:

  1. 2022Reconstructing Training Data with Informed Adversariescited by 143
  2. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  3. 2021Optimal Accounting of Differential Privacy via Characteristic Functioncited by 83
  4. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 56
  5. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 51
  6. 2022Quantum Differential Privacy: An Information Theory Perspectivecited by 32
  7. 2022Defending against Reconstruction Attacks with R'enyi Differential Privacycited by 30
  8. 2021Federated f-Differential Privacycited by 29
  9. 2025Certified Unlearning for Neural Networkscited by 25
  10. 2022CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learningcited by 24
  11. 2023Correlated Noise Provably Beats Independent Noise for Differentially Private Learningcited by 23
  12. 2023Have it your way: Individualized Privacy Assignment for DP-SGDcited by 21
38 more
  1. 2024Differentially Private Next-Token Prediction of Large Language Modelscited by 21
  2. 2023Gaussian Membership Inference Privacycited by 20
  3. 2023Unleashing the Power of Randomization in Auditing Differentially Private MLcited by 19
  4. 2023ViP: A Differentially Private Foundation Model for Computer Visioncited by 17
  5. 2021On the Renyi Differential Privacy of the Shuffle Modelcited by 16
  6. 2023Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacycited by 14
  7. 2021Federated Deep Learning with Bayesian Privacycited by 13
  8. 2023Flow-based Distributionally Robust Optimizationcited by 13
  9. 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
  10. 2023Preserving Node-level Privacy in Graph Neural Networkscited by 11
  11. 2023Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learnerscited by 11
  12. 2022Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMMcited by 10
  13. 2024Shifted Interpolation for Differential Privacycited by 10
  14. 2024Data-adaptive Differentially Private Prompt Synthesis for In-Context Learningcited by 10
  15. 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacycited by 10
  16. 2023ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacycited by 9
  17. 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 9
  18. 2024DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptationcited by 9
  19. 2021Improving Differentially Private SGD via Randomly Sparsified Gradientscited by 8
  20. 2024Beyond the Calibration Point: Mechanism Comparison in Differential Privacycited by 8
  21. 2024Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacementcited by 7
  22. 2021Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learningcited by 6
  23. 2022Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Designcited by 6
  24. 2023Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attackscited by 6
  25. 2025Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learningcited by 6
  26. 2025DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimationcited by 6
  27. 2022The Saddle-Point Accountant for Differential Privacycited by 5
  28. 2023Training Differentially Private Graph Neural Networks with Random Walk Samplingcited by 5
  29. 2023"Private Prediction Strikes Back!'' Private Kernelized Nearest Neighbors with Individual Renyi Filtercited by 5
  30. 2024Differentially Private Representation Learning via Image Captioningcited by 5
  31. 2024DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generatorscited by 5
  32. 2025Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approachcited by 5
  33. 2022Shuffle Gaussian Mechanism for Differential Privacycited by 4
  34. 2022Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learningcited by 4
  35. 2023FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximationscited by 4
  36. 2023A Unified View of Differentially Private Deep Generative Modelingcited by 4
  37. 2024DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuningcited by 4
  38. 2024Adaptively Private Next-Token Prediction of Large Language Modelscited by 4

50 most cited of 84 All 84 (JSON)