FaceCat: Enhancing Face Recognition Security with a Unified Generative Model Framework

arXiv:2404.09193v1 Announce Type: new
Abstract: Face anti-spoofing (FAS) and adversarial detection (FAD) have been regarded as critical technologies to ensure the safety of face recognition systems. As a consequence of their limited practicality and generalization, some existing methods aim to devise a framework capable of concurrently detecting both threats to address the challenge. Nevertheless, these methods still encounter challenges of insufficient generalization and suboptimal robustness, potentially owing to the inherent drawback of discriminative models. Motivated by the rich structural and …

abstract adversarial aim arxiv cs.cv detection face face recognition framework generative recognition safety security systems technologies threats type