Memory-Efficient Federated Adversarial Training with Theoretic Robustness and Low Inconsistency

FedProphet, a novel federated adversarial training framework, can achieve memory efficiency, adversarial robustness, and objective consistency simultaneously by partitioning the large model into small cascaded modules, deriving strong convexity regularization to guarantee robustness, and coordinating the local training of clients based on their hardware resources.