Towards Multi-modal Finger Presentation Attack Detection

Abstract

The wide deployment of biometric verification systems has also unveiled security and privacy issues. Among other vulnerabilities, presentation attacks directed to the capture device pose a severe security threat. That is, a gummy finger (known as presentation attack instrument, PAI) can be used to impersonate another subject and thereby gain illegal access to the system. To prevent such attacks, presentation attack detection (PAD) techniques have been proposed in the last decade. For the particular case of fingerprints, most approaches are based on conventional optical or capacitive sensors, acquiring a single image, and which can thus detect only a limited number of PAIs. In this work, we present a new multi-modal PAD approach based on a recently developed capture device, which is able to acquire four different types of samples: i) finger photos, ii) finger vein samples, iii) multi-spectral short wave infrared images, and iv) laser speckle contrast image sequence samples. Different ad-hoc algorithms have been developed for each set of images. The experimental evaluation over 35 PAIs, part of them used only at the test stage, shows the efficiency of the proposed approach in a realistic scenario, with an APCER of 6.6% for a BPCER of 0.2%.