RESPECT - REliable, Secure and Privacy preserving multi-biometric pErson authentiCaTion

Automated fingerprint recognition systems, while widely used, are still vulnerable to presentation attacks (PAs). The attacks can employ a wide range of presentation attack species (i.e., artifacts), varying from low-cost artifacts to sophisticated materials. A number of presentation attack detection (PAD) approaches have been specifically designed to detect and counteract presentation attacks on fingerprint systems. In this chapter, we study and analyze the well-employed Convolutional Neural Networks (CNN) with different architectures for fingerprint PAD by providing an extensive analysis of 23 different architectures in CNNs. In addition, this chapter presents a new approach introducing vision transformers for fingerprint PAD and validates it on two different public datasets, LivDet2015 and LivDet2019, used for fingerprint PAD. With the analysis of vision transformer-based F-PAD, this chapter covers both spectrum of CNNs and vision transformers to provide the reader with a one-place reference for understanding the performance of various architectures. Vision transformers provide at par results for the fingerprint PAD compared to CNNs with more extensive training duration suggesting its promising nature. In addition, the chapter presents the results for a partial open-set protocol and a true open-set protocol analysis where neither the capture sensor nor the material in the testing set is known at the training phase. With the true open-set protocol analysis, this chapter presents the weakness of both CNN architectures and vision transformers in scaling up to unknown test data, i.e., generalizability challenges.

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.

Biometric systems have experienced a large development over the last years since they are accurate, secure and in many cases, more user convenient than traditional credential-based access control systems. In spite of their benefits, biometric systems are vulnerable to attack presentations, which can be easily carried out by a non-authorised subject without having a deep computational knowledge. This way, he/she can gain access to several applications where biometric systems are frequently deployed, such as bank accounts and smartphone unlocking. In order to mitigate such threats, we present in this work a study on the feasibility of using the Fisher Vector (FV) representation to spot unknown-attack presentations over different biometric modalities such as fingerprint, face and voice. By learning a common feature space from a set of local features, extracted from known samples, the FVs lead to the construction of reliable discriminative models which can successfully distinguish a bona fide presentation from an attack presentation. The experimental evaluation over publicly available databases (i.e. LivDets, CASIA-FASD, SiW-M and ASVspoof, among others) yields error rates outperforming most state-of-the-art algorithms for challenging scenarios where species, recipies or capture devices remain unknown.