Jin-Li Liu

FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning

FUSE is introduced, a structure-aware robust aggregator that uses a small trusted labeled dataset for coefficient recovery, scale and cone-consistency screening, and post-screening step-size control, and improves seed-wise worst-attack accuracy over the strongest baseline on each benchmark by 3.9--30.1 percentage point...