Quadruplet Loss For Improving the Robustness to Face Morphing Attacks

arXiv:2402.14665v1 Announce Type: new
Abstract: Recent advancements in deep learning have revolutionized technology and security measures, necessitating robust identification methods. Biometric approaches, leveraging personalized characteristics, offer a promising solution. However, Face Recognition Systems are vulnerable to sophisticated attacks, notably face morphing techniques, enabling the creation of fraudulent documents. In this study, we introduce a novel quadruplet loss function for increasing the robustness of face recognition systems against morphing attacks. Our approach involves specific sampling of face image quadruplets, combined with …

abstract arxiv attacks biometric cs.cv deep learning documents enabling face face recognition identification loss personalized recognition robust robustness security solution systems technology type vulnerable