mlsanityData to 7 Oct 2026

Algorithms with More Granular Differential Privacy Guarantees

arXiv 2209.04053 ↗First posted 8 Sep 2022cs.CR cs.DS cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Differential privacy is often applied with a privacy parameter that is larger than the theory suggests is ideal; various informal justifications for tolerating large privacy parameters have been proposed. In this work, we consider partial differential privacy (DP), which allows quantifying the privacy guarantee on a per-attribute basis. In this framework, we study several basic data analysis and learning tasks, and design algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person (i.e., all the attributes).

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 117 references that are in the map. First posted on arXiv 8 Sep 2022.

Builds on

45 of 117 references.

References · 45

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  2. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  3. 2021Membership Inference Attacks From First Principlescited by 839
  4. 2017Renyi Differential Privacycited by 643
  5. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  6. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  7. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 213
  8. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
  9. 2016Concentrated Differential Privacycited by 139
  10. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  11. 2018Distributed Differential Privacy via Shufflingcited by 115
  12. 2017Finite Sample Differentially Private Confidence Intervalscited by 103
33 more
  1. 2015Algorithmic Stability for Adaptive Data Analysiscited by 88
  2. 2013Fingerprinting Codes and the Price of Approximate Differential Privacycited by 81
  3. 2018Private PAC learning implies finite Littlestone dimensioncited by 73
  4. 2021Learning with User-Level Privacycited by 72
  5. 2014Private Learning and Sanitization: Pure vs. Approximate Differential Privacycited by 62
  6. 2015Differentially Private Release and Learning of Threshold Functionscited by 58
  7. 2016Discrete Distribution Estimation under Local Privacycited by 58
  8. 2017Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12cited by 42
  9. 2022Geographic Spines in the 2020 Census Disclosure Avoidance Systemcited by 42
  10. 2020Learning discrete distributions: user vs item-level privacycited by 41
  11. 2022Debugging Differential Privacy: A Case Study for Privacy Auditingcited by 39
  12. 2015Local, Private, Efficient Protocols for Succinct Histogramscited by 35
  13. 2015Simultaneous Private Learning of Multiple Conceptscited by 34
  14. 2019SoK: Differential Privaciescited by 33
  15. 2014Sample Complexity Bounds on Differentially Private Learning via Communication Complexitycited by 31
  16. 2019Privately Learning Thresholds: Closing the Exponential Gapcited by 30
  17. 2017Optimal Schemes for Discrete Distribution Estimation under Locally Differential Privacycited by 28
  18. 2016PrivTree: A Differentially Private Algorithm for Hierarchical Decompositionscited by 22
  19. 2017Heavy Hitters and the Structure of Local Privacycited by 20
  20. 2013Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimationcited by 19
  21. 2019Context-Aware Local Differential Privacycited by 18
  22. 2013Efficient Algorithms for Privately Releasing Marginals via Convex Relaxationscited by 17
  23. 2019Separating Local & Shuffled Differential Privacy via Histogramscited by 16
  24. 2015Optimality of the Laplace Mechanism in Differential Privacycited by 15
  25. 2020The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noisecited by 15
  26. 2013Blowfish Privacy: Tuning Privacy-Utility Trade-offs using Policiescited by 12
  27. 2020Connecting Robust Shuffle Privacy and Pan-Privacycited by 12
  28. 2018Towards Instance-Optimal Private Query Releasecited by 9
  29. 2020Robust and Private Learning of Halfspacescited by 7
  30. 2019Element Level Differential Privacy: The Right Granularity of Privacycited by 6
  31. 2019Capacity Bounded Differential Privacycited by 5
  32. 2017Differential Privacy as a Causal Propertycited by 4
  33. 2020Multi-Central Differential Privacycited by 3

Built on by

Cited by year

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

4 papers.

  1. 2023Private Learning with Public Featurescited by 6
  2. 2024Analyzing Inference Privacy Risks Through Gradients in Machine Learningcited by 4
  3. 2024Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacycited by 2
  4. 2025Machine Learning with Privacy for Protected Attributescited by 2