MLSD-GAN -- Generating Strong High Quality Face Morphing Attacks using Latent Semantic Disentanglement

arXiv:2404.12679v1 Announce Type: new
Abstract: Face-morphing attacks are a growing concern for biometric researchers, as they can be used to fool face recognition systems (FRS). These attacks can be generated at the image level (supervised) or representation level (unsupervised). Previous unsupervised morphing attacks have relied on generative adversarial networks (GANs). More recently, researchers have used linear interpolation of StyleGAN-encoded images to generate morphing attacks. In this paper, we propose a new method for generating high-quality morphing attacks using StyleGAN disentanglement. …

abstract arxiv attacks biometric cs.cr cs.cv face face recognition gan generated generative image quality recognition representation researchers semantic systems type unsupervised