mlsanityData to 7 Oct 2026

Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI

arXiv 2503.16233 ↗First posted 20 Mar 2025cs.LG cs.CR cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables collaborative model training while preserving data privacy; however, balancing privacy preservation (PP) and fairness poses significant challenges. In this paper, we present the first unified large-scale empirical study of privacy-fairness-utility trade-offs in FL, advancing toward responsible AI deployment. Specifically, we systematically compare Differential Privacy (DP), Homomorphic Encryption (HE), and Secure Multi-Party Computation (SMC) with fairness-aware optimizers including q-FedAvg, q-MAML, Ditto, evaluating their performance under IID and non-IID scenarios using benchmark (MNIST, Fashion-MNIST) and real-world datasets (Alzheimer's MRI, credit-card fraud detection). Our analysis reveals HE and SMC significantly outperform DP in achieving equitable outcomes under data skew, although at higher computational costs. Remarkably, we uncover unexpected interactions: DP mechanisms can negatively impact fairness, and fairness-aware optimizers can inadvertently reduce privacy effectiveness. We conclude with practical guidelines for designing robust FL systems that deliver equitable, privacy-preserving, and accurate outcomes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

25 of 50 references.

References · 25

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2018Federated Learning with Non-IID Datacited by 1,099
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  6. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  7. 2019Agnostic Federated Learningcited by 451
  8. 2019Fair Resource Allocation in Federated Learningcited by 389
  9. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  11. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  12. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
13 more
  1. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  2. 2019Putting Fairness Principles into Practice: Challenges, Metrics, and Improvementscited by 70
  3. 2023Federated Learning of Gboard Language Models with Differential Privacycited by 64
  4. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  5. 2022Privacy-Preserving Aggregation in Federated Learning: A Surveycited by 25
  6. 2021Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learningcited by 13
  7. 2022PrivFairFL: Privacy-Preserving Group Fairness in Federated Learningcited by 13
  8. 2022Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasurescited by 11
  9. 2021Federated Learning Meets Fairness and Differential Privacycited by 9
  10. 2020Addressing the Real-world Class Imbalance Problem in Dermatologycited by 5
  11. 2024PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learningcited by 4
  12. 2023TrojFair: Trojan Fairness Attackscited by 2
  13. 2024Evaluating Fairness in Transaction Fraud Models: Fairness Metrics, Bias Audits, and Challengescited by 2

Built on by

Not cited yet.