提出首个可验证公平性保障的联邦学习框架，兼顾隐私与算法公正。
Privacy-Preserving Federated Learning with Verifiable Fairness Guarantees
- 用同态加密和安全多方计算实现隐私保护下的公平性验证。
- 公平性偏差从0.231降至0.031，计算开销仅增加2.3倍。
- 适合医疗、金融等需隐私与公平双重保障的场景。
联邦学习可在不集中敏感数据的前提下实现跨机构协同训练，但如何在异构数据分布下保障算法公平性并维护隐私仍是未解难题。本文提出CryptoFair-FL，首个在形式化安全定义下提供可验证公平性保障的密码学框架。该方法结合加法同态加密与安全多方计算，无需泄露受保护属性分布或个体预测即可验证群组平等性与均等机会指标。提出的批量验证协议将计算复杂度从O(n²)降至O(n log n)，同时满足(δ=0.5, Δ=10⁻⁶)-差分隐私。理论分析揭示公平性验证的隐私成本下界，表明所提协议达到近最优隐私-公平权衡。在四个基准数据集（MIMIC-IV医疗记录、Adult Income、CelebA及新构建的FedFair-100）上的实验表明，该框架将群组平等性差异从0.231降至0.031，计算开销仅为标准联邦平均的2.3倍。框架有效抵御属性推断攻击，在所有配置下对抗成功率低于0.05。结果为受监管行业部署公平感知联邦学习提供了可行路径。
原文摘要 · Abstract (English)
Federated learning enables collaborative model training across distributed institutions without centralizing sensitive data; however, ensuring algorithmic fairness across heterogeneous data distributions while preserving privacy remains fundamentally unresolved. This paper introduces CryptoFair-FL, a novel cryptographic framework providing the first verifiable fairness guarantees for federated learning systems under formal security definitions. The proposed approach combines additively homomorphic encryption with secure multi-party computation to enable privacy-preserving verification of demographic parity and equalized odds metrics without revealing protected attribute distributions or individual predictions. A novel batched verification protocol reduces computational complexity from BigO(n^2) to BigO(n \log n) while maintaining (\dparam, \deltap)-differential privacy with dparam = 0.5 and deltap = 10^{-6}. Theoretical analysis establishes information-theoretic lower bounds on the privacy cost of fairness verification, demonstrating that the proposed protocol achieves near-optimal privacy-fairness tradeoffs. Comprehensive experiments across four benchmark datasets (MIMIC-IV healthcare records, Adult Income, CelebA, and a novel FedFair-100 benchmark) demonstrate that CryptoFair-FL reduces fairness violations from 0.231 to 0.031 demographic parity difference while incurring only 2.3 times computational overhead compared to standard federated averaging. The framework successfully defends against attribute inference attacks, maintaining adversarial success probability below 0.05 across all tested configurations. These results establish a practical pathway for deploying fairness-aware federated learning in regulated industries requiring both privacy protection and algorithmic accountability.
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。