Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs

arXiv:2404.06025v1 Announce Type: new
Abstract: Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a recently proposed morphing attack that has achieved state-of-the-art performance for representation-based morphing attacks. However, none of the existing research on DiMs have leveraged the iterative nature of DiMs and left the DiM model as a black box, treating it no differently than one …

abstract aim algorithms art arxiv attacks biometric cs.ai cs.cv diffusion face face recognition however image information multiple performance recognition representation state systems threat type