Cross-database and cross-attack Iris presentation attack detection using micro stripes analyses

Iris presentation attack detection (PAD) is still an unsolved problem mainly due to the various spoof attack strategies and poor generalisation on unseen attackers. In this paper, the merits of both light field (LF) imaging and deep learning (DL) are leveraged to combine 2D texture and 3D geometry features for iris liveness detection. By exploring off‐the‐shelf deep features of planar‐oriented and sequence‐oriented deep neural networks (DNNs) on the rendered focal stack, the proposed framework excavates the differences in 3D geometric structure and 2D spatial texture between bona fide and spoofing irises captured by LF cameras. A group of pre‐trained DL models are adopted as feature extractor and the parameters of SVM classifiers are optimised on a limited number of samples. Moreover, two‐branch feature fusion further strengthens the framework's robustness and reliability against severe motion blur, noise, and other degradation factors. The results of comparative experiments indicate that variants of the proposed framework significantly surpass the PAD methods that take 2D planar images or LF focal stack as input, even recent state‐of‐the‐art (SOTA) methods fined‐tuned on the adopted database. Presentation attacks, including printed papers, printed photos, and electronic displays, can be accurately detected without fine‐tuning a bulky CNN. In addition, ablation studies validate the effectiveness of fusing geometric structure and spatial texture features. The results of multi‐class attack detection experiments also verify the good generalisation ability of the proposed framework on unseen presentation attacks.

Human iris is considered a reliable and accurate modality for biometric recognition due to its unique texture information. Reliability and accuracy of iris biometric modality have prompted its large-scale deployment for critical applications such as border control and national identification projects. The extensive growth of iris recognition systems has raised apprehensions about the susceptibility of these systems to various presentation attacks. In this thesis, a novel iris presentation attack using deep learning based synthetically generated iris images is presented. Utilizing the generative capability of deep convolutional generative adversarial networks and iris quality metrics, a new framework, named as iDCGAN is proposed for creating realistic appearing synthetic iris images. In-depth analysis is performed using quality score distributions of real and synthetically generated iris images to understand the effectiveness of the proposed approach. We also demonstrate that synthetically generated iris images can be used to attack existing iris recognition systems. As synthetically generated iris images can be effectively deployed in iris presentation attacks, it is important to develop accurate iris presentation attack detection algorithms which can distinguish such synthetic iris images from real iris images. For this purpose, a novel structural and textural feature-based iris presentation attack detection framework (DESIST) is proposed. The key emphasis of DESIST is on developing a unified framework for detecting a medley of iris presentation attacks, including synthetic iris. Experimental evaluations showcase the efficacy of the proposed DESIST framework in detecting synthetic iris presentation attacks.

The adoption of large-scale iris recognition systems around the world has brought to light the importance of detecting presentation attack images (textured contact lenses and printouts). This work presents a new approach in iris Presentation Attack Detection (PAD), by exploring combinations of Convolutional Neural Networks (CNNs) and transformed input spaces through binarized statistical image features (BSIF). Our method combines lightweight CNNs to classify multiple BSIF views of the input image. Following explorations on complementary input spaces leading to more discriminative features to detect presentation attacks, we also propose an algorithm to select the best (and most discriminative) predictors for the task at hand.An ensemble of predictors makes use of their expected individual performances to aggregate their results into a final prediction. Results show that this technique improves on the current state of the art in iris PAD, outperforming the winner of LivDet-Iris2017 competition both for intra- and cross-dataset scenarios, and illustrating the very difficult nature of the cross-dataset scenario.

Iris Presentation Attack Detection (PAD) is essential to secure iris recognition systems. Recent iris PAD solutions achieved good performance by leveraging deep learning techniques. However, most results were reported under intra-database scenarios, and it is unclear if such solutions can generalize well across databases and capture spectra. These PAD methods run the risk of overfitting because of the binary label supervision during the network training, which serves global information learning but weakens the capture of local discriminative features. This chapter presents a novel attention-based deep pixel-wise binary supervision (A-PBS) method. A-PBS utilizes pixel-wise supervision to capture the fine-grained pixel/patch-level cues and attention mechanism to guide the network to automatically find regions where most contribute to an accurate PAD decision. Extensive experiments are performed on six NIR and one visible-light iris databases to show the effectiveness and robustness of proposed A-PBS methods. We additionally conduct extensive experiments under intra-/cross-database and intra-/cross-spectrum for detailed analysis. The results of our experiments indicate the generalizability of the A-PBS iris PAD approach.

Face Recognition Systems (FRS) are vulnerable to spoofing attacks (a.k.a presentation attacks), which can be carried out by presenting a printed photo (print-photo), displaying a photo (display-photo), or displaying a video (replay-video). The issue of presentation attacks can be alleviated by algorithms known as presentation attack detection (PAD) mechanisms. In this paper, we propose a novel framework based on Hierarchical Cosine/Spherical Linear Interpolation of deep learning feature vectors followed by training a Linear SVM for PAD Classification. The deep learning feature vectors are extracted from existing networks trained on the Imagenet dataset. Our proposed approach hierarchically interpolates the extracted feature vectors using Cosine/Spherically Linear Interpolation, followed by using a Linear SVM for classification, and sum-rule fusion for generating final scores. We show our results on cross-dataset PAD for the classifier trained on OULU P1 Dataset and tested on Replay Mobile Dataset. We compare it with the current state-of-the-art (SOTA) algorithms published in the literature and achieve considerably lower detection error-rate (D-EER). The extraction of features from pre-trained networks makes our approach simple to use, apart from it, giving highly accurate results, which are much better than current SOTA.

Face recognition systems face real challenges from various presentation attacks. New, more sophisticated methods of presentation attacks are becoming more difficult to detect using traditional face recognition systems. Thermal infrared imaging offers specific physical properties that may boost presentation attack detection capabilities. The aim of this paper is to present outcomes of investigations on the detection of various face presentation attacks in thermal infrared in various conditions including thermal heating of masks and various states of subjects. A thorough analysis of presentation attacks using printed and displayed facial photographs, 3D-printed, custom flexible 3D-latex and silicone masks is provided. The paper presents the intensity analysis of thermal energy distribution for specific facial landmarks during long-lasting experiments. Thermalization impact, as well as varying the subject’s state due to physical effort on presentation attack detection are investigated. A new thermal face spoofing dataset is introduced. Finally, a two-step deep learning-based method for the detection of presentation attacks is presented. Validation results of a set of deep learning methods across various presentation attack instruments are presented.

Biometric systems are vulnerable to presentation attacks (PAs) performed using various PA instruments (PAIs). Even though there are numerous PA detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with de-folding and de-mixing to derive the task-specific representation for PAD. During de-folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing the generative loss. While de-mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing the interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with the state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% equal error rate (EER) in OULU-NPU and MSU-MFSD, exceeding the baseline performance by 9.54%. The source code of the proposed technique is available at https://github.com/kongzhecn/dfdm.

Iris recognition technology has attracted an increasing interest in the last decades in which we have witnessed a migration from research laboratories to real-world applications. The deployment of this technology raises questions about the main vulnerabilities and security threats related to these systems. Among these threats, presentation attacks stand out as some of the most relevant and studied. Presentation attacks can be defined as the presentation of human characteristics or artifacts directly to the capture device of a biometric system trying to interfere with its normal operation. In the case of the iris, these attacks include the use of real irises as well as artifacts with different levels of sophistication such as photographs or videos. This chapter introduces iris Presentation Attack Detection (PAD) methods that have been developed to reduce the risk posed by presentation attacks. First, we summarize the most popular types of attacks including the main challenges to address. Second, we present a taxonomy of PAD methods as a brief introduction to this very active research area. Finally, we discuss the integration of these methods into iris recognition systems according to the most important scenarios of practical application.

In this work, we propose a novel Cyclic Image Translation Generative Adversarial Network (CIT-GAN) for multi-domain style transfer. To facilitate this, we introduce a Styling Network that has the capability to learn style characteristics of each domain represented in the training dataset. The Styling Network helps the generator to drive the translation of images from a source domain to a reference domain and generate synthetic images with style characteristics of the reference domain. The learned style characteristics for each domain depend on both the style loss and domain classification loss. This induces variability in style characteristics within each domain. The proposed CIT-GAN is used in the context of iris presentation attack detection (PAD) to generate synthetic presentation attack (PA) samples for classes that are under-represented in the training set. Evaluation using current state-of-the-art iris PAD methods demonstrates the efficacy of using such synthetically generated PA samples for training PAD methods. Further, the quality of the synthetically generated samples is evaluated using Frechet Inception Distance (FID) score. Results show that the quality of synthetic images generated by the proposed method is superior to that of other competing methods, including StarGan.

The rapid advancement of premium smartphones with sophisticated high resolution cameras has enabled reliable and convenient contactless acquisition of fingerprint biometrics, making them suitable for verification at scale. However, as with other biometric systems, contactless fingerprint verification remains vulnerable to presentation attacks. Many Presentation Attack Detection (PAD) methods rely on supervised learning that requires labelled attack data, which limits generalisation. We propose an unsupervised PAD approach based on the Denoising Diffusion Probabilistic Model (DDPM). The system is trained only on bona fide samples and makes decisions via score level fusion of two deep similarity measures, yielding robustness to unseen attacks without access to attack labels. We further provide a Jacobian based theoretical analysis that explains why diffusion reconstructions are well suited to PAD. Using Frobenius and spectral norms together with a log determinant surrogate, we show that the iterative refinement in diffusion models preserves ridge aligned structure while contracting off manifold artifacts, thereby accounting for the observed empirical gains over single shot alternatives. In addition, we introduce a new fingerphoto presentation attack dataset comprising 101 subjects with 6,060 bona fide and 1,818 attack images captured on recent smartphones under diverse conditions. Benchmarking across four datasets shows that the proposed method is effective in practice, improving PAD performance and outperforming strong supervised baselines and recent state of the art methods in unseen attack scenarios. We report uncertainty estimates and non parametric statistical summaries across datasets and PAIs (Presentation Attack Instruments), which indicate consistent advantages without significant regressions, supporting the suitability of diffusion based PAD for deployment.

State-of-the-art spoof detection methods tend to overfit to the spoof types seen during training and fail to generalize to unknown spoof types. Given that face anti-spoofing is inherently a local task, we propose a face anti-spoofing framework, namely Self-Supervised Regional Fully Convolutional Network (SSR-FCN), that is trained to learn local discriminative cues from a face image in a self-supervised manner. The proposed framework improves generalizability while maintaining the computational efficiency of holistic face anti-spoofing approaches (< 4 ms on a Nvidia GTX 1080Ti GPU). The proposed method is interpretable since it localizes which parts of the face are labeled as spoofs. Experimental results show that SSR-FCN can achieve TDR = 65% @ 2.0% FDR when evaluated on a dataset comprising of 13 different spoof types under unknown attacks while achieving competitive performances under standard benchmark datasets (Oulu-NPU, CASIA-MFSD, and Replay-Attack).

This chapter presents a comprehensive study on the application of stimulated pupillary light reflex to presentation attack detection (PAD) that can be used in iris recognition systems. A pupil, when stimulated by visible light in a predefined manner, may offer sophisticated dynamic liveness features that cannot be acquired from dead eyes or other static objects such as printed contact lenses, paper printouts, or prosthetic eyes. Modeling of pupil dynamics requires a few seconds of observation under varying light conditions that can be supplied by a visible light source in addition to the existing near-infrared illuminants used in iris image acquisition. The central element of the presented approach is an accurate modeling and classification of pupil dynamics that makes mimicking an actual eye reaction difficult. This chapter discusses new data-driven models of pupil dynamics based on recurrent neural networks and compares their PAD performance to solutions based on the parametric Clynes–Kohn model and various classification techniques. Experiments with 166 distinct eyes of 84 subjects show that the best data-driven solution, one based on long short-term memory, was able to correctly recognize 99.97% of attack presentations and 98.62% of normal pupil reactions. In the approach using the Clynes–Kohn parametric model of pupil dynamics, we were able to perfectly recognize abnormalities and correctly recognize 99.97% of normal pupil reactions on the same dataset with the same evaluation protocol as the data-driven approach. This means that the data-driven solutions favorably compare to the parametric approaches, which require model identification in exchange for a slightly better performance. We also show that observation times may be as short as 3 s when using the parametric model, and as short as 2 s when applying the recurrent neural network without substantial loss in accuracy. Along with this chapter we also offer: (a) all time series representing pupil dynamics for 166 distinct eyes used in this study, (b) weights of the trained recurrent neural network offering the best performance, (c) source codes of the reference PAD implementation based on Clynes–Kohn parametric model, and (d) all PAD scores that allow the reproduction of the plots presented in this chapter. To our best knowledge, this chapter proposes the first database of pupil measurements dedicated to presentation attack detection and the first evaluation of recurrent neural network-based modeling of pupil dynamics and PAD.

Today, face biometric systems are becoming widely accepted as a standard method for identity authentication in many security settings. For example, their deployment in automated border control gates plays a crucial role in accurate document authentication and reduced traveler flow rates in congested border zones. The proliferation of such systems is further spurred by the advent of portable devices. On the one hand, modern smartphone and tablet cameras have in-built user authentication applications while on the other hand, their displays are being consistently exploited for face spoofing. Similar to biometric systems of other physiological biometric identifiers, face biometric systems have their own unique set of potential vulnerabilities. In this work, these vulnerabilities (presentation attacks) are being explored via a biologically-inspired presentation attack detection model which is termed “BIOPAD.” Our model employs Gabor features in a feedforward hierarchical structure of layers that progressively process and train from visual information of people's faces, along with their presentation attacks, in the visible and near-infrared spectral regions. BIOPAD's performance is directly compared with other popular biologically-inspired layered models such as the “Hierarchical Model And X” (HMAX) that applies similar handcrafted features, and Convolutional Neural Networks (CNN) that discover low-level features through stochastic descent training. BIOPAD shows superior performance to both HMAX and CNN in all of the three presentation attack databases examined and these results were consistent in two different classifiers (Support Vector Machine and k-nearest neighbor). In certain cases, our findings have shown that BIOPAD can produce authentication rates with 99% accuracy. Finally, we further introduce a new presentation attack database with visible and near-infrared information for direct comparisons. Overall, BIOPAD's operation, which is to fuse information from different spectral bands at both feature and score levels for the purpose of face presentation attack detection, has never been attempted before with a biologically-inspired algorithm. Obtained detection rates are promising and confirm that near-infrared visual information significantly assists in overcoming presentation attacks.

Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases.

A fingerphoto is obtained by imaging a human finger using a basic smartphone camera. Although impressive advances have been made to accurately match fingerphotos, this technology is vulnerable to presentation attacks (PAs). These algorithms do not generalize well in the presence of new presentation attacks. While previous research on this issue is limited, this paper systematically evaluates fingerphoto presentation attack detection (PAD) algorithms under unknown attacks. The proposed assessment compares different Convolutional Neural Networks (CNNs) on the IIITD Smartphone Fingerphoto database with spoof data including printout and various display attacks. These images used for the experiments were acquired indoors and subjected to background (i.e., white or natural) and capture device (i.e., Nokia or OPO) variations. Preliminary results show that the PAD based on AlexNet is robust under most types of replica unseen during the training of the detector.