Zhuohua Qiu

FedMOP: Achieving Enhanced Privacy and Performance in Federated Learning via Momentum Orthogonal Projection

Federated Learning (FL) faces a fundamental dilemma: existing defenses against gradient leakage attacks (GLAs) invariably sacrifice model performance for privacy protection through noise injection or gradient clip. We introduce Federated Learning with Momentum-Based Orthogonal Projection (FedMOP), a