Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI
Year: 2025
Type: conference-paper
Abstract: 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.
Institutions: Virginia Tech, DEVCOM Army Research Laboratory, United States Army
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: bronze
Awards: Collaborative Research: CNS: Medium: Energy Centric Wireless Sensor Node System for Smart Farms, III: Medium: Collaborative Research: MUDL: Multidimensional Uncertainty-Aware Deep Learning Framework, Collaborative Research: SaTC: CORE: Medium: Using Intelligent Conversational Agents to Empower Adolescents to be Resilient Against Cybergrooming, G7452299184
OpenAlex ID: W4415195254