Federated Multitask Learning with Manifold Regularization for Face Spoof Attack Detection

Abstract

Face recognition has been widely used in personal authentication, especially on edge computing devices. However, face recognition systems suffer from face spoof attack. In this paper, a novel method for face spoof attack detection in edge computing scenarios is proposed. It is based on federated learning and improves traditional federated learning with multitask learning and manifold regularization, which is known as federated learning for face spoof attack detection (FedFSAD). In this way, local model learning is completed on edge devices and global model learning only depends on the trained local models without using the original image data. Besides, the performance is improved by imposing hypergraph manifold regularization in the global training of multitask learning. The results of comprehensive experiments show that the detection performance is improved by about 10% and robust against stragglers and network delays, which indicates the effectiveness of FedFSAD.