RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility

ICLR 2026 Conference Submission22677 Authors

Keywords: Federated Learning, Fairness, Privacy, Adversarial Representation Learning, Uncertainty Quantification

TL;DR: RESFL is an FL framework that suppresses sensitive attributes via adversarial representation learning and improves group fairness via uncertainty-guided aggregation, delivering strong privacy–fairness–utility trade-offs on FACET and CARLA.

Abstract: Federated Learning (FL) has gained prominence in machine learning applications across critical domains, offering collaborative model training without centralized data aggregation. However, FL frameworks that protect privacy often sacrifice fairness and reliability; differential privacy reduces data leakage but hides sensitive attributes needed for bias correction, worsening performance gaps across demographic groups. This work explores the trade-off between privacy and fairness in FL-based object detection and introduces RESFL, an integrated solution optimizing both. RESFL incorporates adversarial privacy disentanglement and uncertainty-guided fairness-aware aggregation. The adversarial component uses a gradient reversal layer to remove sensitive attributes, reducing privacy risks while maintaining fairness. The uncertainty-aware aggregation employs an evidential neural network to weight client updates adaptively, prioritizing contributions with lower fairness disparities and higher confidence. This ensures robust and equitable FL model updates. We demonstrate the effectiveness of RESFL in high-stakes autonomous vehicle scenarios, where it achieves high mAP on FACET and CARLA, reduces membership-inference attack success by 37%, reduces equality-of-opportunity gap by 17% relative to the FedAvg baseline, and maintains superior adversarial robustness. However, RESFL is inherently domain-agnostic and thus applicable to a broad range of application domains beyond autonomous driving.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 22677