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.

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.

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.

Deep Learning has enabled many advances in machine learning applications in the last few years. However, since current Deep Learning algorithms require much energy for computations, there are growing concerns about the associated environmental costs. Energy-efficient Deep Learning has received much attention from researchers and has already made much progress in the last couple of years. This paper aims to gather information about these advances from the literature and show how and at which points along the lifecycle of Deep Learning (IT-Infrastructure, Data, Modeling, Training, Deployment, Evaluation) it is possible to reduce energy consumption.

In the past decade, globalization and digitization have not only changed the way we work, but also the environment in which we work. More and more companies are introducing desk sharing office concepts in which employees must share a workstation. However, this poses challenges for ergonomic workplace design as constant and ergonomically correct workstation settings can hardly be guaranteed. Neglecting ergonomics at workplace, though, can cause musculoskeletal disorders. Therefore, a concept and prototype for a system are proposed which automatically adjusts the workstation to the individual's anthropometric characteristics. A setup of different mechanical and electronical components using microcontrollers, ultrasonic distance sensors and linear actuators assures an automatic adjustment where users only must sign in with their ID. An initial field study shows that the system can achieve high user acceptance. Simplicity, speed, and convenience are seen as added value of the system. The results have potential for future studies.

Artificial Intelligence (AI) is drastically transforming the world around us. Rather than replacing humans, hybrid intelligence combines human and machine intelligence to leverage each of their individual strengths. We summarize different requirements and approaches identified to achieve hybrid intelligence and focus on conversational AI to build a cognitive agent that supports knowledge management within an organization. The agent automatically extracts knowledge from artifacts provided or published by the us- ers. In addition, the knowledge base steadily grows while the agent talks to the users and the users provide feedback and the system is continuously learning to extract new types of entities and relations to answer more questions based on the knowledge graph and to access other sources of information. The first types of entities and relations extracted already support users in finding colleagues with relevant skills or inter- ests. Based on information provided by the agent, collaboration among employees and, thus, knowledge sharing and transfer is encouraged. The collaboration between the cognitive agent as an AI artifact and employees combined with a system that learns and adapts while in use stressing explainability and trust in its answers entails a step towards hybrid intelligence.

Digital technologies have become increasingly important for educational institutions since the Covid-19 pandemic. In this paper, we present an artificially intelligent assistant system that supports students and prospective students on different levels. In addition to an AI-based chatbot as the central communication element, the virtual guidance system includes planning, study analysis, and motivation applications. To evaluate how the assistant can best address students’ needs, a qualitative focus group study with eight current students was conducted in April 2022, involving first a user testing of the chatbot prototype and second an assessment of different concept sketches for the planner and motivator applications. Results from the user testing of the chatbot suggest the importance of a vivid persona and appealing design, accurate, guided, direct answering, and optional push messaging. In the second part concerning planner and motivator, the students expressed the wish to integrate predominantly functions, which help to prepare on time for exams and ideally bundle the applications on one platform to avoid switching between different platforms. Furthermore, participants voiced privacy concerns, as well as an increase in distraction and competitive pressure through gamification. The findings were used to further develop and refine the digital assistant before launch. They give detailed insight into why and how integrated, digital assistants can be successful in educational settings and can be used for future research in the emerging research field of AI in teaching and learning.