Robust Face Presentation Attack Detection with Multi-channel Neural Networks

Abstract

AbstractVulnerability against presentation attacks remains a challenging issue limiting the reliable use of face recognition systems. Though several methods have been proposed in the literature for the detection of presentation attacks, majority of these methods fail in generalizing to unseen attacks and environments. Since the quality of attack instruments keeps getting better, the difference between bona fide and attack samples is diminishing making it harder to distinguish them using the visible spectrum alone. In this context, multi-channel presentation attack detection methods have been proposed as a solution to secure face recognition systems. Even with multiple channels, special care needs to be taken to ensure that the model generalizes well in challenging scenarios. In this chapter, we present three different strategies to use multi-channel information for presentation attack detection. Specifically, we present different architecture choices for fusion, along with ad hoc loss functions as opposed to standard classification objective. We conduct an extensive set of experiments in the HQ-WMCA dataset, which contains a wide variety of attacks and sensing channels together with challenging unseen attack evaluation protocols. We make the protocol, source codes, and data publicly available to enable further extensions of the work.