Conditional Identity Disentanglement for Differential Face Morph Detection
This addresses security vulnerabilities in biometric systems like passports for government and security agencies, with incremental improvements in cross-dataset performance.
The paper tackles the problem of detecting face morph attacks in identification documents by proposing a conditional generative network that disentangles identities from morphed images, achieving 3% BPCER at 10% APCER in intra-dataset evaluation and 4.6% BPCER at 10% APCER in cross-dataset evaluation, outperforming state-of-the-art methods by at least 13.9%.
We present the task of differential face morph attack detection using a conditional generative network (cGAN). To determine whether a face image in an identification document, such as a passport, is morphed or not, we propose an algorithm that learns to implicitly disentangle identities from the morphed image conditioned on the trusted reference image using the cGAN. Furthermore, the proposed method can also recover some underlying information about the second subject used in generating the morph. We performed experiments on AMSL face morph, MorGAN, and EMorGAN datasets to demonstrate the effectiveness of the proposed method. We also conducted cross-dataset and cross-attack detection experiments. We obtained promising results of 3% BPCER @ 10% APCER on intra-dataset evaluation, which is comparable to existing methods; and 4.6% BPCER @ 10% APCER on cross-dataset evaluation, which outperforms state-of-the-art methods by at least 13.9%.