mlsanityData to 14 Oct 2026

Differential Privacy has Bounded Impact on Fairness in Classification

arXiv 2210.16242 ↗First posted 28 Oct 2022cs.LG cs.CR stat.MLcited by 18

Not on the map. Why?

Abstract (arXiv)

We theoretically study the impact of differential privacy on fairness in classification. We prove that, given a class of models, popular group fairness measures are pointwise Lipschitz-continuous with respect to the parameters of the model. This result is a consequence of a more general statement on accuracy conditioned on an arbitrary event (such as membership to a sensitive group), which may be of independent interest. We use this Lipschitz property to prove a non-asymptotic bound showing that, as the number of samples increases, the fairness level of private models gets closer to the one of their non-private counterparts. This bound also highlights the importance of the confidence margin of a model on the disparate impact of differential privacy.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

26 of 51 references.

References · 26

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2017Counterfactual Fairnesscited by 804
  6. 2017Renyi Differential Privacycited by 650
  7. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  8. 2020Fairness in Machine Learning: A Surveycited by 370
  9. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  10. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  11. 2020On the Privacy Risks of Algorithmic Fairnesscited by 82
  12. 2018Differentially Private Fair Learningcited by 76
14 more
  1. 2020When Machine Learning Meets Privacy: A Survey and Outlookcited by 68
  2. 2020Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacycited by 61
  3. 2019Fair Decision Making using Privacy-Protected Datacited by 58
  4. 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
  5. 2021Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Datacited by 48
  6. 2022Differential Privacy and Fairness in Decisions and Learning Tasks: A Surveycited by 47
  7. 2020Fair Learning with Private Demographic Datacited by 46
  8. 2018Blind Justice: Fairness with Encrypted Sensitive Attributescited by 41
  9. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?cited by 33
  10. 2019Stable and Fair Classificationcited by 25
  11. 2022How unfair is private learning ?cited by 18
  12. 2020Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracycited by 13
  13. 2022FairGrad: Fairness Aware Gradient Descentcited by 8
  14. 2022Differentially Private Learning with Margin Guaranteescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 6; 2026: 3.

18 papers.

Sort:

  1. 2024The Better Angels of Machine Personality: How Personality Relates to LLM Safetycited by 21
  2. 2024Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Modelscited by 18
  3. 2024A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Resultscited by 6
  4. 2024The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Modelscited by 5
  5. 2023FairDP: Certified Fairness with Differential Privacycited by 4
  6. 2023On the Impact of Multi-dimensional Local Differential Privacy on Fairnesscited by 4
  7. 2023SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learningcited by 4
  8. 2024Differentially Private Fair Binary Classificationscited by 3
  9. 2025SoK: What Makes Private Learning Unfair?cited by 3
  10. 2025Learning with Differentially Private (Sliced) Wasserstein Gradientscited by 2
  11. 2025Private Rate-Constrained Optimization with Applications to Fair Learningcited by 1
  12. 2025Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classificationcited by 1
6 more
  1. 2024On the Impact of Output Perturbation on Fairness in Binary Linear Classificationcited by 0
  2. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  3. 2025The Fair Game: Auditing & Debiasing AI Algorithms Over Timecited by 0
  4. 2026Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimationcited by 0
  5. 2026Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systemscited by 0
  6. 2026Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithmscited by 0