mlsanityData to 14 Oct 2026

Fair Decision Making using Privacy-Protected Data

arXiv 1905.12744 ↗First posted 29 May 2019cs.DBcited by 58

Not on the map. Why?

Abstract (arXiv)

Data collected about individuals is regularly used to make decisions that impact those same individuals. We consider settings where sensitive personal data is used to decide who will receive resources or benefits. While it is well known that there is a tradeoff between protecting privacy and the accuracy of decisions, we initiate a first-of-its-kind study into the impact of formally private mechanisms (based on differential privacy) on fair and equitable decision-making. We empirically investigate novel tradeoffs on two real-world decisions made using U.S. Census data (allocation of federal funds and assignment of voting rights benefits) as well as a classic apportionment problem. Our results show that if decisions are made using an ε-differentially private version of the data, under strict privacy constraints (smaller ε), the noise added to achieve privacy may disproportionately impact some groups over others. We propose novel measures of fairness in the context of randomized differentially private algorithms and identify a range of causes of outcome disparities.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 12; 2023: 14; 2024: 13; 2025: 5; 2026: 5.

58 papers.

Sort:

  1. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  2. 2021Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Datacited by 48
  3. 2022Differential Privacy and Fairness in Decisions and Learning Tasks: A Surveycited by 47
  4. 2022Pruning has a disparate impact on model accuracycited by 44
  5. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?cited by 33
  6. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  7. 2022Disparate Impact in Differential Privacy from Gradient Misalignmentcited by 31
  8. 2021Privacy Regularization: Joint Privacy-Utility Optimization in Language Modelscited by 30
  9. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  10. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  11. 2022Differential Privacy has Bounded Impact on Fairness in Classificationcited by 18
  12. 2022Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairnesscited by 13
38 more
  1. 2021A Fairness Analysis on Private Aggregation of Teacher Ensemblescited by 11
  2. 2022What You See is What You Get: Principled Deep Learning via Distributional Generalizationcited by 11
  3. 2022Post-processing of Differentially Private Data: A Fairness Perspectivecited by 9
  4. 2022Fair NLP Models with Differentially Private Text Encoderscited by 9
  5. 2022Survey on Fairness Notions and Related Tensionscited by 9
  6. 2023An Empirical Analysis of Fairness Notions under Differential Privacycited by 9
  7. 2022SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensemblescited by 8
  8. 2023FFPDG: Fast, Fair and Private Data Generationcited by 8
  9. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?cited by 7
  10. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  11. 2024A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Resultscited by 6
  12. 2022Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attackscited by 5
  13. 2023Fairness and Sequential Decision Making: Limits, Lessons, and Opportunitiescited by 5
  14. 2023(Local) Differential Privacy has NO Disparate Impact on Fairnesscited by 5
  15. 2023On the Fairness Impacts of Private Ensembles Modelscited by 4
  16. 2023Understanding User Intent Modeling for Conversational Recommender Systems: A Systematic Literature Reviewcited by 4
  17. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4
  18. 2023A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacycited by 4
  19. 2023SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learningcited by 4
  20. 2024PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learningcited by 4
  21. 2021On the impossibility of non-trivial accuracy under fairness constraintscited by 3
  22. 2024Differentially Private Fair Binary Classificationscited by 3
  23. 2024PFGuard: A Generative Framework with Privacy and Fairness Safeguardscited by 3
  24. 2022Spending Privacy Budget Fairly and Wiselycited by 2
  25. 2023Privacy and Bias Analysis of Disclosure Avoidance Systemscited by 2
  26. 2023Automated discovery of trade-off between utility, privacy and fairness in machine learning modelscited by 2
  27. 2024MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakagecited by 2
  28. 2024De-amplifying Bias from Differential Privacy in Language Model Fine-tuningcited by 2
  29. 2024Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processescited by 2
  30. 2024Differentially Private Random Feature Modelcited by 2
  31. 2025Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Modelscited by 2
  32. 2024Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacycited by 1
  33. 2024Privacy at a Price: Exploring its Dual Impact on AI Fairnesscited by 1
  34. 2024Efficient and Private Marginal Reconstruction with Local Non-Negativitycited by 1
  35. 2024Fair and Welfare-Efficient Constrained Multi-matchings under Uncertaintycited by 1
  36. 2025RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utilitycited by 1
  37. 2025SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Trainingcited by 1
  38. 2026Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspectivecited by 1

50 most cited of 58 All 58 (JSON)