3D Face Morphing Attack Generation using Non-Rigid Registration
This addresses security risks in commercial applications like e-commerce and e-banking by enhancing attack generation for testing and improving FRS robustness, though it is incremental as it builds on existing morphing techniques.
The paper tackles the vulnerability of Face Recognition Systems to facial morphing attacks by proposing a new method for generating 3D face morphs from point clouds, achieving a Generalized Morphing Attack Potential of 97.93%, which outperforms the existing state-of-the-art at 81.61%.
Face Recognition Systems (FRS) are widely used in commercial environments, such as e-commerce and e-banking, owing to their high accuracy in real-world conditions. However, these systems are vulnerable to facial morphing attacks, which are generated by blending face color images of different subjects. This paper presents a new method for generating 3D face morphs from two bona fide point clouds. The proposed method first selects bona fide point clouds with neutral expressions. The two input point clouds were then registered using a Bayesian Coherent Point Drift (BCPD) without optimization, and the geometry and color of the registered point clouds were averaged to generate a face morphing point cloud. The proposed method generates 388 face-morphing point clouds from 200 bona fide subjects. The effectiveness of the method was demonstrated through extensive vulnerability experiments, achieving a Generalized Morphing Attack Potential (G-MAP) of 97.93%, which is superior to the existing state-of-the-art (SOTA) with a G-MAP of 81.61%.