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 defeat the system. Existing PA detection schemes do not have good generalization capability and often fail in cross-dataset scenarios, where training and testing are performed on vastly different datasets. In this work, we address this problem by fusing the outputs of three Convolutional Neural Network (CNN) based PA detectors, each of which examines different portions of the input image. The first CNN (I-CNN) focuses on the iris region only, the second CNN (F-CNN) uses the entire ocular region and the third CNN (S-CNN) uses a subset of patches sampled from the ocular region. Experiments conducted on two publicly available datasets (LivDetW15 and BERC-IF) and on a proprietary dataset (IrisID) confirm that the use of a bag of CNNs is effective in improving the generalizability of PA detectors.

Iris + Ocular: Generalized Iris Presentation Attack Detection Using Multiple Convolutional Neural Networks

Launched in 2013, LivDet-Iris is an international competition series open to academia and industry with the aim to assess and report advances in iris Presentation Attack Detection (PAD). This paper presents results from the fourth competition of the series: LivDet-Iris 2020. This year's competition introduced several novel elements: (a) incorporated new types of attacks (samples displayed on a screen, cadaver eyes and prosthetic eyes), (b) initiated LivDet-Iris as an on-going effort, with a testing protocol available now to everyone via the Biometrics Evaluation and Testing (BEAT)* open-source platform to facilitate reproducibility and benchmarking of new algorithms continuously, and (c) performance comparison of the submitted entries with three baseline methods (offered by the University of Notre Dame and Michigan State University), and three open-source iris PAD methods available in the public domain. The best performing entry to the competition reported a weighted average APCER of 59.10% and a BPCER of 0.46% over all five attack types. This paper serves as the latest evaluation of iris PAD on a large spectrum of presentation attack instruments.

Iris Liveness Detection Competition (LivDet-Iris) - The 2020 Edition

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 outperforms 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.

D-NetPAD: An Explainable and Interpretable Iris Presentation Attack Detector

Convolutional Neural Networks (CNNs) are being increasingly used to address the problem of iris presentation attack detection. In this work, we propose an explainable attention-guided iris presentation attack detector (AG-PAD) to augment CNNs with attention mechanisms and to provide visual explanations of model predictions. Two types of attention modules are independently placed on top of the last convolutional layer of the backbone network. Specifically, the channel attention module is used to model the inter-channel relationship between features, while the position attention module is used to model inter-spatial relationship between features. An element-wise sum is employed to fuse these two attention modules. Further, a novel hierarchical attention mechanism is introduced. Experiments involving both a JHU-APL proprietary dataset and the benchmark LivDet-Iris-2017 dataset suggest that the proposed method achieves promising detection results while explaining occurrences of salient regions for discriminative feature learning. To the best of our knowledge, this is the first work that exploits the use of attention mechanisms in iris presentation attack detection.

/pdf/an-explainable-attention-guided-iris-presentation-attack-52galj47ww.pdf

An Explainable Attention-Guided Iris Presentation Attack Detector

With the widespread use of biometric systems, the demographic bias problem raises more attention. Although many studies addressed bias issues in biometric verification, there are no works that analyze the bias in presentation attack detection (PAD) decisions. Hence, we investigate and analyze the demographic bias in iris PAD algorithms in this paper. To enable a clear discussion, we adapt the notions of differential performance and differential outcome to the PAD problem. We study the bias in iris PAD using three baselines (hand-crafted, transfer-learning, and training from scratch) using the NDCLD-2013 database. The experimental results point out that female users will be significantly less protected by the PAD, in comparison to males.

Demographic Bias in Presentation Attack Detection of Iris Recognition Systems

Iris recognition systems are vulnerable to presentation attacks where an adversary employs artifacts such as 2D prints of the eye, plastic eyes, and cosmetic contact lenses to obfuscate their own identity or to spoof the identity of another subject. In this work, we design a Convolutional Neural Network (CNN) architecture for presentation attack detection, that is observed to have good cross-dataset generalization capability. The salient features of the proposed approach include: (a) the use of the pre-normalized iris rather than the normalized iris, thereby avoiding spatial information loss; (b) the tessellation of the iris region into overlapping patches to enable data augmentation as well as to learn features that are location agnostic; (c) fusion of information across patches to enhance detection accuracy; (d) incorporating a "segmentation mask" in order to automatically learn the relative importance of the pupil and iris regions; (e) generation of a "heat map" that displays patch-wise presentation attack information, thereby accounting for artifacts that may impact only a small portion of the iris region. Experiments confirm the efficacy of the proposed approach.

/pdf/convolutional-neural-networks-for-iris-presentation-attack-iodrbwfeev.pdf

Steven Hoffman

Papers

Convolutional Neural Networks for Iris Presentation Attack Detection: Toward Cross-Dataset and Cross-Sensor Generalization

Iris + Ocular: Generalized Iris Presentation Attack Detection Using Multiple Convolutional Neural Networks