SCPAD: An approach to explore optical characteristics for robust static presentation attack detection

Presentation attack detection approaches have achieved great progress on various attack types while adversarial learning technology has become a new threat to these approaches. Now few works are devoted to developing a robust detection method for both physical spoofing faces and digital adversarial faces. In this paper, we find that fake face images from printed photos and replayed videos have a different optical characteristic from the real ones, and the adversarial samples generated by various attacking methods retain this characteristic. By exploring this characteristic, we propose the Spectral Characteristic Presentation Attack Detection (SCPAD), a new approach that detects presentation attacks by reconstructing the color space of input images, which also performs well on adversarial samples. More specifically, a new HSCbb color space is manually constructed by studying the difference in albedo intensity between real faces and fake faces. Then the difference between real and spoofing faces can be effectively magnified and modeled by color texture features with the shallow convolutional network. The experimental results show that our proposed method consistently outperforms the state-of-the-art methods on adversarial faces and also achieves competitive performance on fake faces.