mlsanityData to 7 Oct 2026

PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning

arXiv 2407.15224 ↗First posted 21 Jul 2024cs.LG cs.AI cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

Training and deploying Machine Learning models that simultaneously adhere to principles of fairness and privacy while ensuring good utility poses a significant challenge. The interplay between these three factors of trustworthiness is frequently underestimated and remains insufficiently explored. Consequently, many efforts focus on ensuring only two of these factors, neglecting one in the process. The decentralization of the datasets and the variations in distributions among the clients exacerbate the complexity of achieving this ethical trade-off in the context of Federated Learning (FL). For the first time in FL literature, we address these three factors of trustworthiness. We introduce PUFFLE, a high-level parameterised approach that can help in the exploration of the balance between utility, privacy, and fairness in FL scenarios. We prove that PUFFLE can be effective across diverse datasets, models, and data distributions, reducing the model unfairness up to 75%, with a maximum reduction in the utility of 17% in the worst-case scenario, while maintaining strict privacy guarantees during the FL training.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 21 Jul 2024.

Builds on

32 of 55 references.

References · 32

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  7. 2014Certifying and removing disparate impactcited by 715
  8. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  9. 2017Renyi Differential Privacycited by 643
  10. 2019Agnostic Federated Learningcited by 451
  11. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  12. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
20 more
  1. 2017On Fairness and Calibrationcited by 406
  2. 2019Fair Resource Allocation in Federated Learningcited by 389
  3. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  4. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  5. 2020Threats to Federated Learning: A Surveycited by 171
  6. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  7. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  8. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  9. 2020On the Privacy Risks of Algorithmic Fairnesscited by 82
  10. 2021Federated Learning with Fair Averagingcited by 59
  11. 2019Fair Decision Making using Privacy-Protected Datacited by 58
  12. 2020Mitigating Bias in Federated Learningcited by 56
  13. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  14. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  15. 2022Disparate Impact in Differential Privacy from Gradient Misalignmentcited by 31
  16. 2023Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregationcited by 16
  17. 2022PrivFairFL: Privacy-Preserving Group Fairness in Federated Learningcited by 13
  18. 2023Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utilitycited by 10
  19. 2021Federated Learning Meets Fairness and Differential Privacycited by 9
  20. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utilitycited by 1
  2. 2025Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AIcited by 0
  3. 2025FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluationcited by 0
  4. 2025FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utilitycited by 0