Hierarchical Generative Network for Face Morphing Attacks

arXiv:2403.11101v1 Announce Type: new
Abstract: Face morphing attacks circumvent face recognition systems (FRSs) by creating a morphed image that contains multiple identities. However, existing face morphing attack methods either sacrifice image quality or compromise the identity preservation capability. Consequently, these attacks fail to bypass FRSs verification well while still managing to deceive human observers. These methods typically rely on global information from contributing images, ignoring the detailed information from effective facial regions. To address the above issues, we propose a …

abstract arxiv attack methods attacks capability cs.cv face face recognition generative hierarchical however human identity image multiple network preservation quality recognition systems type verification