Face Recognition systems (FRS) have been found to be vulnerable to morphing attacks, where the morphed face image is generated by blending the face images from contributory data subjects. This work presents a novel direction for generating face-morphing attacks in 3D. To this extent, we introduced a novel approach based on blending 3D face point clouds corresponding to contributory data subjects. The proposed method generates 3D face morphing by projecting the input 3D face point clouds onto depth maps and 2D color images, followed by image blending and wrapping operations performed independently on the color images and depth maps. We then back-projected the 2D morphing color map and the depth map to the point cloud using the canonical (fixed) view. Given that the generated 3D face morphing models will result in holes owing to a single canonical view, we have proposed a new algorithm for hole filling that will result in a high-quality 3D face morphing model. Extensive experiments were conducted on the newly generated 3D face dataset comprising 675 3D scans corresponding to 41 unique data subjects and a publicly available database (Facescape) with 100 data subjects. Experiments were performed to benchmark the vulnerability of the {proposed 3D morph-generation scheme against} automatic 2D, 3D FRS, and human observer analysis. We also presented a quantitative assessment of the quality of the generated 3D face-morphing models using eight different quality metrics. Finally, we propose three different 3D face Morphing Attack Detection (3D-MAD) algorithms to benchmark the performance of 3D face morphing attack detection techniques.

翻译：人脸识别系统（FRS）被发现易受变形攻击，此类攻击通过混合多名贡献主体的面部图像生成变形人脸图像。本文提出了一种全新的三维面部变形攻击生成方向。为此，我们引入了一种基于混合对应贡献主体三维人脸点云的新方法。该方法通过将输入的三维人脸点云投影至深度图和二维彩色图像，随后分别对彩色图像和深度图进行图像混合与包裹操作，从而生成三维人脸变形。接着，我们利用固定视角将二维变形彩色图和深度图反向投影至点云。由于单一固定视角生成的二维变形彩色图和深度图会产生空洞，我们提出了一种新的空洞填充算法，以获得高质量的三维人脸变形模型。我们在新生成的三维人脸数据集上进行了大量实验，该数据集包含41位独立贡献主体的675个三维扫描，以及一个包含100位贡献主体的公开数据库（Facescape）。通过实验基准测试，评估了所提出的三维变形生成方案对自动二维、三维人脸识别系统及人类观察者分析的脆弱性。我们还使用八种不同质量指标对生成的三维人脸变形模型进行了定量评估。最后，我们提出了三种不同的三维人脸变形攻击检测（3D-MAD）算法，以基准测试三维人脸变形攻击检测技术的性能。