首次系统分析联邦学习中隐私、公平与准确的权衡，助力负责任AI落地。
Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI
- 对比三种隐私技术与公平优化器在不同数据分布下的表现。
- 同态加密和安全多方计算在数据偏斜下更公平，但计算开销大。
- 发现隐私机制可能损害公平性，公平优化器可能削弱隐私保护。
联邦学习（FL）可在保护数据隐私的同时实现协作建模，但平衡隐私保护（PP）与公平性面临重大挑战。本文首次开展大规模实证研究，系统分析联邦学习中隐私-公平-效用的权衡，推动负责任AI部署。我们系统比较了差分隐私（DP）、同态加密（HE）、安全多方计算（SMC）与公平感知优化器（q-FedAvg、q-MAML、Ditto），在独立同分布（IID）与非独立同分布（non-IID）场景下，使用基准数据集（MNIST、Fashion-MNIST）和真实数据集（阿尔茨海默病脑影像、信用卡欺诈检测）进行评估。结果表明，HE与SMC在数据偏斜条件下显著优于DP，能实现更均衡的结果，但计算成本更高。值得注意的是，我们发现了意外交互：DP机制可能对公平性产生负面影响，而公平感知优化器可能无意中降低隐私有效性。最后，我们提出实用设计指南，帮助构建兼具公平性、隐私保护与高准确性的联邦学习系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。