Secure Learning Algorithm for Multimodal Biometric Systems against Spoof Attacks
Spoof attack is one of the major challenges that can decline the security and reliability of the biometric systems. Multimodal biometric systems are commonly believed to be more resilient against spoof attacks than systems using single biometric trait. However, a recent study has questioned, contrary to a common claim, that multimodal systems can be cracked by spoofing only one trait and pointed out the need of developing new algorithms to enhance robustness of the multimodal systems against spoof attacks. In this paper, the authors propose a new learning algorithm that can improve the security of multimodal systems against spoof attacks.