mlsanityData to 7 Oct 2026

On the Privacy Risks of Algorithmic Fairness

arXiv 2011.03731 ↗First posted 7 Nov 2020stat.ML cs.CR cs.CYcited by 82

Not on the map. Why?

Abstract (arXiv)

Algorithmic fairness and privacy are essential pillars of trustworthy machine learning. Fair machine learning aims at minimizing discrimination against protected groups by, for example, imposing a constraint on models to equalize their behavior across different groups. This can subsequently change the influence of training data points on the fair model, in a disproportionate way. We study how this can change the information leakage of the model about its training data. We analyze the privacy risks of group fairness (e.g., equalized odds) through the lens of membership inference attacks: inferring whether a data point is used for training a model. We show that fairness comes at the cost of privacy, and this cost is not distributed equally: the information leakage of fair models increases significantly on the unprivileged subgroups, which are the ones for whom we need fair learning. We show that the more biased the training data is, the higher the privacy cost of achieving fairness for the unprivileged subgroups will be. We provide comprehensive empirical analysis for general machine learning algorithms.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 22; 2023: 23; 2024: 15; 2025: 10; 2026: 7.

82 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  3. 2023Low-Cost High-Power Membership Inference Attackscited by 99
  4. 2023Machine Unlearning: Solutions and Challengescited by 85
  5. 2023Bias Testing and Mitigation in LLM-based Code Generationcited by 53
  6. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learningcited by 47
  7. 2021Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communitiescited by 40
  8. 2022Disparate Impact in Differential Privacy from Gradient Misalignmentcited by 31
  9. 2022Pre-trained Perceptual Features Improve Differentially Private Image Generationcited by 28
  10. 2023Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishingcited by 28
  11. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  12. 2022The privacy issue of counterfactual explanations: explanation linkage attackscited by 20
38 more
  1. 2022How unfair is private learning ?cited by 18
  2. 2022Differential Privacy has Bounded Impact on Fairness in Classificationcited by 18
  3. 2023Unraveling Privacy Risks of Individual Fairness in Graph Neural Networkscited by 16
  4. 2023Unlocking Accuracy and Fairness in Differentially Private Image Classificationcited by 16
  5. 2022Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairnesscited by 13
  6. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  7. 2022Conflicting Interactions Among Protection Mechanisms for Machine Learning Modelscited by 12
  8. 2022The Impact of Differential Privacy on Group Disparity Mitigationcited by 11
  9. 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstructioncited by 10
  10. 2023Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utilitycited by 10
  11. 2021SoK: Machine Learning Governancecited by 9
  12. 2022Fair NLP Models with Differentially Private Text Encoderscited by 9
  13. 2022On the Alignment of Group Fairness with Attribute Privacycited by 9
  14. 2023An Empirical Analysis of Fairness Notions under Differential Privacycited by 9
  15. 2024Counterfactual Concept Bottleneck Modelscited by 7
  16. 2022When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributescited by 6
  17. 2022Data Privacy and Trustworthy Machine Learningcited by 6
  18. 2023(Un)fair devices: Moving beyond AI accuracy in personal sensingcited by 6
  19. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  20. 2024Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learningcited by 6
  21. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6
  22. 2024A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Resultscited by 6
  23. 2025Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyondcited by 6
  24. 2022Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attackscited by 5
  25. 2023When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attackscited by 5
  26. 2022Fairness in Forecasting of Observations of Linear Dynamical Systemscited by 4
  27. 2023Group-blind optimal transport to group parity and its constrained variantscited by 4
  28. 2023On the Impact of Multi-dimensional Local Differential Privacy on Fairnesscited by 4
  29. 2023SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learningcited by 4
  30. 2024PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learningcited by 4
  31. 2025Trustworthy AI Must Account for Interactionscited by 4
  32. 2022Exploring the Unfairness of DP-SGD Across Settingscited by 3
  33. 2023SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmarkcited by 3
  34. 2024Regulation Games for Trustworthy Machine Learningcited by 3
  35. 2024Differentially Private Fair Binary Classificationscited by 3
  36. 2025Enabling Group Fairness in Graph Unlearning via Bi-level Debiasingcited by 3
  37. 2022How Much User Context Do We Need? Privacy by Design in Mental Health NLP Applicationcited by 2
  38. 2022On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Modelscited by 2

50 most cited of 82 All 82 (JSON)