OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglement
This addresses a security threat in biometric systems, offering an incremental improvement over existing morphing attack detection methods.
The paper tackles the problem of morphing attacks on deep face recognition systems by proposing OrthoMAD, a method that uses a novel regularization term to disentangle identity information into orthogonal latent vectors, achieving state-of-the-art results in most experiments on the FRLL dataset with a small ResNet-18 backbone.
Morphing attacks are one of the many threats that are constantly affecting deep face recognition systems. It consists of selecting two faces from different individuals and fusing them into a final image that contains the identity information of both. In this work, we propose a novel regularisation term that takes into account the existent identity information in both and promotes the creation of two orthogonal latent vectors. We evaluate our proposed method (OrthoMAD) in five different types of morphing in the FRLL dataset and evaluate the performance of our model when trained on five distinct datasets. With a small ResNet-18 as the backbone, we achieve state-of-the-art results in the majority of the experiments, and competitive results in the others. The code of this paper will be publicly available.