Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
This work addresses the problem of fair and standardized evaluation for face anti-spoofing methods, which is crucial for improving security in facial recognition systems, though it is incremental in nature.
The paper tackles the challenge of generalization in face presentation attack detection by introducing an open-source evaluation framework called face-GPAD, which includes a large aggregated dataset and two novel protocols for assessing resolution variations and adversarial conditions.
Over the past few years, Presentation Attack Detection (PAD) has become a fundamental part of facial recognition systems. Although much effort has been devoted to anti-spoofing research, generalization in real scenarios remains a challenge. In this paper we present a new open-source evaluation framework to study the generalization capacity of face PAD methods, coined here as face-GPAD. This framework facilitates the creation of new protocols focused on the generalization problem establishing fair procedures of evaluation and comparison between PAD solutions. We also introduce a large aggregated and categorized dataset to address the problem of incompatibility between publicly available datasets. Finally, we propose a benchmark adding two novel evaluation protocols: one for measuring the effect introduced by the variations in face resolution, and the second for evaluating the influence of adversarial operating conditions.