Develops and empirically validates an end-to-end MPC protocol for post-market fairness monitoring in algorithmic hiring that integrates legal and industrial constraints.
Privfairfl: Privacy-preserving group fairness in federated learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
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.
citing papers explorer
-
Co-designing for Compliance: Multi-party Computation Protocols for Post-Market Fairness Monitoring in Algorithmic Hiring
Develops and empirically validates an end-to-end MPC protocol for post-market fairness monitoring in algorithmic hiring that integrates legal and industrial constraints.
-
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.