Depth-guided Robust Face Morphing Attack Detection

Recently, morphing attack detection (MAD) solutions have achieved remarkable success with the aid of deep learning techniques. Despite the good performance achieved by binary label or binary pixel-wise supervised MAD models, the robustness of such models drops when facing variations in morphing attacks. In this work, we propose a novel process that leverages facial depth information to build a robust and generalized MAD. The depth map, representing the 3D shape of the face in a 2D image, is more informative compared to binary and binary pixel-wise map labels. To validate the idea we synthetically generated 3D depth map ground truth. Furthermore, we introduce a novel MAD architecture designed to capture subtle information from the 3D depth data. In addition, we analyze the training loss formulation to further enhance the MAD performance. Driven by the need for developing MAD solutions while preserving the privacy of individuals for legal and ethical reasons, we conduct our experiments on privacy-friendly synthetic training data and authentic evaluation data. The experimental results on existing public datasets in SYN-MAD 22 competition demonstrate the effectiveness of our proposed solution in terms of both robustness and generalization.