Landmark Enforcement and Style Manipulation for Generative Morphing
This work addresses a security vulnerability in facial recognition systems by enhancing morph generation techniques, though it appears incremental as it builds on existing StyleGAN methods.
The paper tackled the problem of identity loss in GAN-based facial morph generation for bypassing facial recognition systems by proposing a landmark enforcement method and latent space manipulation, achieving morphs that inherit geometric identities from both source faces and improved high-frequency reconstruction.
Morph images threaten Facial Recognition Systems (FRS) by presenting as multiple individuals, allowing an adversary to swap identities with another subject. Morph generation using generative adversarial networks (GANs) results in high-quality morphs unaffected by the spatial artifacts caused by landmark-based methods, but there is an apparent loss in identity with standard GAN-based morphing methods. In this paper, we propose a novel StyleGAN morph generation technique by introducing a landmark enforcement method to resolve this issue. Considering this method, we aim to enforce the landmarks of the morph image to represent the spatial average of the landmarks of the bona fide faces and subsequently the morph images to inherit the geometric identity of both bona fide faces. Exploration of the latent space of our model is conducted using Principal Component Analysis (PCA) to accentuate the effect of both the bona fide faces on the morphed latent representation and address the identity loss issue with latent domain averaging. Additionally, to improve high frequency reconstruction in the morphs, we study the train-ability of the noise input for the StyleGAN2 model.