D-NetPAD: An Explainable and Interpretable Iris Presentation Attack Detector
This addresses security vulnerabilities in iris recognition systems for biometric authentication, but it is incremental as it adapts an existing neural network architecture to a specific domain.
The paper tackles iris presentation attack detection by proposing D-NetPAD, a DenseNet-based method that achieves a true detection rate of 98.58% at a false detection rate of 0.2% on a proprietary dataset and outperforms state-of-the-art methods on the LivDet-2017 dataset.
An iris recognition system is vulnerable to presentation attacks, or PAs, where an adversary presents artifacts such as printed eyes, plastic eyes, or cosmetic contact lenses to circumvent the system. In this work, we propose an effective and robust iris PA detector called D-NetPAD based on the DenseNet convolutional neural network architecture. It demonstrates generalizability across PA artifacts, sensors and datasets. Experiments conducted on a proprietary dataset and a publicly available dataset (LivDet-2017) substantiate the effectiveness of the proposed method for iris PA detection. The proposed method results in a true detection rate of 98.58\% at a false detection rate of 0.2\% on the proprietary dataset and outperfoms state-of-the-art methods on the LivDet-2017 dataset. We visualize intermediate feature distributions and fixation heatmaps using t-SNE plots and Grad-CAM, respectively, in order to explain the performance of D-NetPAD. Further, we conduct a frequency analysis to explain the nature of features being extracted by the network. The source code and trained model are available at https://github.com/iPRoBe-lab/D-NetPAD.