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

arXiv: https://arxiv.org/abs/2503.16233 · HTML: https://mlsanity.com/paper/2503.16233/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements](https://mlsanity.com/paper/1901.04562/) (2019)
- [Federated Learning of Gboard Language Models with Differential Privacy](https://mlsanity.com/paper/2305.18465/) (2023)
- [Privacy-Preserving Aggregation in Federated Learning: A Survey](https://mlsanity.com/paper/2203.17005/) (2022)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning](https://mlsanity.com/paper/2105.07985/) (2021)
- [PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning](https://mlsanity.com/paper/2205.11584/) (2022)
- [Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures](https://mlsanity.com/paper/2204.06273/) (2022)
- [Federated Learning Meets Fairness and Differential Privacy](https://mlsanity.com/paper/2108.09932/) (2021)
- [Addressing the Real-world Class Imbalance Problem in Dermatology](https://mlsanity.com/paper/2010.04308/) (2020)
- [PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning](https://mlsanity.com/paper/2407.15224/) (2024)
- [TrojFair: Trojan Fairness Attacks](https://mlsanity.com/paper/2312.10508/) (2023)
- [Evaluating Fairness in Transaction Fraud Models: Fairness Metrics, Bias Audits, and Challenges](https://mlsanity.com/paper/2409.04373/) (2024)

## 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.