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

TL;DR

This paper introduces MLSD-GAN, a novel method using StyleGAN's latent space disentanglement to generate highly realistic and diverse face morphing attacks that effectively fool face recognition systems.

Contribution

MLSD-GAN is the first approach to leverage spherical interpolation of disentangled latents for high-quality face morphing attacks, improving attack realism and diversity.

Findings

MLSD-GAN successfully fools state-of-the-art face recognition systems.

The method produces highly realistic and diverse morphing images.

It demonstrates a significant security threat to biometric systems.

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. Our approach, called MLSD-GAN, spherically interpolates the disentangled latents to produce realistic and diverse morphing attacks. We evaluate the vulnerability of MLSD-GAN on two deep-learning-based FRS techniques. The results show that MLSD-GAN poses a significant threat to FRS, as it can generate morphing attacks that are highly effective at fooling these systems.