SynMorph: Generating Synthetic Face Morphing Dataset with Mated Samples

Abstract--Face morphing attack detection (MAD) algorithms have become essential to overcome the vulnerability of face recognition systems. To solve the lack of large-scale and public-available datasets due to privacy concerns and restrictions, in this work we propose a new method to generate a synthetic face morphing dataset with 2450 identities and more than 100k morphs. The proposed synthetic face morphing dataset is unique for its high-quality samples, different types of morphing algorithms, and the generalization for both single and differential morphing attack detection algorithms. For experiments, we apply face image quality assessment and vulnerability analysis to evaluate the proposed synthetic face morphing dataset from the perspective of biometric sample quality and morphing attack potential on face recognition systems. The results are benchmarked with an existing SOTA synthetic dataset and a representative non-synthetic and indicate improvement compared with the SOTA. Additionally, we design different protocols and study the applicability of using the proposed synthetic dataset on training morphing attack detection algorithms. Nonetheless, with the improvement develop generalized and robust MAD algorithms and testing of FRS in generalization and the development datasets to evaluate and benchmark existing algorithms of image manipulation techniques, it is also shown that from different developers. However, due to privacy regulations, FRS is vulnerable to various types of attacks [2] [3]. Hence, face samples are considered sensitive data, which it is essential to develop corresponding attack detection makes it challenging to collect the dataset on a large scale algorithms to protect the FRS from potential attacks.