mlsanityData to 7 Oct 2026

Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey

arXiv 2202.08187 ↗First posted 16 Feb 2022cs.LG cs.AIcited by 47

Not on the map. Why?

Abstract (arXiv)

This paper surveys recent work in the intersection of differential privacy (DP) and fairness. It reviews the conditions under which privacy and fairness may have aligned or contrasting goals, analyzes how and why DP may exacerbate bias and unfairness in decision problems and learning tasks, and describes available mitigation measures for the fairness issues arising in DP systems. The survey provides a unified understanding of the main challenges and potential risks arising when deploying privacy-preserving machine-learning or decisions-making tasks under a fairness lens.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 29 of its 63 references that are in the map. First posted on arXiv 16 Feb 2022.

Builds on

29 of 63 references.

References · 29

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2018A Reductions Approach to Fair Classificationcited by 585
  4. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  5. 2018Scalable Private Learning with PATEcited by 266
  6. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  7. 2018Hessian-based Analysis of Large Batch Training and Robustness to Adversariescited by 87
  8. 2018Differentially Private Fair Learningcited by 76
  9. 2020Lagrangian Duality for Constrained Deep Learningcited by 72
  10. 2017Efficient Private ERM for Smooth Objectivescited by 61
  11. 2020Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacycited by 61
  12. 2019Fair Decision Making using Privacy-Protected Datacited by 58
17 more
  1. 2020Mitigating Bias in Federated Learningcited by 56
  2. 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
  3. 2021Antipodes of Label Differential Privacy: PATE and ALIBIcited by 50
  4. 2020Fair Learning with Private Demographic Datacited by 46
  5. 2020Chasing Your Long Tails: Differentially Private Prediction in Health Care Settingscited by 37
  6. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  7. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?cited by 32
  8. 2020Differentially Private and Fair Classification via Calibrated Functional Mechanismcited by 20
  9. 2020Improving Fairness and Privacy in Selection Problemscited by 16
  10. 2020Bias and Variance of Post-processing in Differential Privacycited by 14
  11. 2020Google COVID-19 Community Mobility Reports: Anonymization Process Description (version 1.1)cited by 13
  12. 2021A Fairness Analysis on Private Aggregation of Teacher Ensemblescited by 11
  13. 2020Differential Privacy of Hierarchical Census Data: An Optimization Approachcited by 9
  14. 2021Federated Learning Meets Fairness and Differential Privacycited by 9
  15. 2022Post-processing of Differentially Private Data: A Fairness Perspectivecited by 9
  16. 2019Differential Privacy for Power Grid Obfuscationcited by 5
  17. 2021Observations on the Bias of Nonnegative Mechanisms for Differential Privacycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 13; 2024: 13; 2025: 9; 2026: 5.

47 papers.

Sort:

  1. 2022Pruning has a disparate impact on model accuracycited by 43
  2. 2022How unfair is private learning ?cited by 18
  3. 2022Differential Privacy has Bounded Impact on Fairness in Classificationcited by 18
  4. 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstructioncited by 10
  5. 2022Survey on Fairness Notions and Related Tensionscited by 9
  6. 2022On the Alignment of Group Fairness with Attribute Privacycited by 9
  7. 2024Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learningcited by 9
  8. 2022SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensemblescited by 8
  9. 2023Disentangling and Operationalizing AI Fairness at LinkedIncited by 7
  10. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  11. 2024A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Resultscited by 6
  12. 2024Certification for Differentially Private Prediction in Gradient-Based Trainingcited by 6
35 more
  1. 2023(Local) Differential Privacy has NO Disparate Impact on Fairnesscited by 5
  2. 2023On the Fairness Impacts of Private Ensembles Modelscited by 4
  3. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  4. 2023On the Impact of Multi-dimensional Local Differential Privacy on Fairnesscited by 4
  5. 2023A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacycited by 4
  6. 2023SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learningcited by 4
  7. 2024Differentially Private Clustered Federated Learningcited by 4
  8. 2025Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithmscited by 4
  9. 2025Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacycited by 4
  10. 2023FairDP: Certified Fairness with Differential Privacycited by 3
  11. 2025SoK: What Makes Private Learning Unfair?cited by 3
  12. 2023Privacy and Bias Analysis of Disclosure Avoidance Systemscited by 2
  13. 2023Trading-off price for data quality to achieve fair online allocationcited by 2
  14. 2023Automated discovery of trade-off between utility, privacy and fairness in machine learning modelscited by 2
  15. 2023On The Fairness Impacts of Hardware Selection in Machine Learningcited by 2
  16. 2024Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processescited by 2
  17. 2024FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptationcited by 2
  18. 2024Combining Machine Learning Defenses without Conflictscited by 2
  19. 2025Learning with Differentially Private (Sliced) Wasserstein Gradientscited by 2
  20. 2025Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clippingcited by 2
  21. 2024Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacycited by 1
  22. 2024REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Valuescited by 1
  23. 2024Differential Privacy Overview and Fundamental Techniquescited by 1
  24. 2024Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquirycited by 1
  25. 2025SoK: Data Minimization in Machine Learningcited by 1
  26. 2025Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGDcited by 1
  27. 2026Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Datacited by 1
  28. 2024On the Impact of Output Perturbation on Fairness in Binary Linear Classificationcited by 0
  29. 2024Differentially Private Data Release on Graphs: Inefficiencies and Unfairnesscited by 0
  30. 2025Fair Play for Individuals, Foul Play for Groups? Auditing Anonymization's Impact on ML Fairnesscited by 0
  31. 2025Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classificationcited by 0
  32. 2026Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimationcited by 0
  33. 2026How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluationcited by 0
  34. 2026SoK: Colluding Adversaries in Machine Learning Pipelinescited by 0
  35. 2026Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithmscited by 0