RESFL integrates adversarial feature disentanglement and uncertainty-aware client weighting in federated learning to reduce membership inference attacks and equality-of-opportunity gaps while preserving model utility for object detection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility
RESFL integrates adversarial feature disentanglement and uncertainty-aware client weighting in federated learning to reduce membership inference attacks and equality-of-opportunity gaps while preserving model utility for object detection.