In the presence of data and computational resources, machine learning can be used to synthesize software automatically. For example, machines are now capable of learning complicated pattern recognition tasks and sophisticated decision policies, two key capabilities in autonomous cyber-physical systems. Unfortunately, humans find software synthesized by machine learning algorithms difficult to interpret, which currently limits their use in safety-critical applications such as medical diagnosis and avionic systems. In particular, successful deployments of safety-critical systems mandate the execution of rigorous verification activities, which often rely on human insights, e.g., to identify scenarios in which the system shall be tested. A natural pathway towards a viable verification strategy for such systems is to leverage formal verification techniques, which, in the presence of a formal specification, can provide definitive guarantees with little human intervention. However, formal verification suffers from scalability issues with respect to system complexity. In this thesis, we investigate the limits of current formal verification techniques when applied to a class of machine learning models called tree ensembles, and identify model-specific characteristics that can be exploited to improve the performance of verification algorithms when applied specifically to tree ensembles. To this end, we develop two formal verification techniques specifically for tree ensembles, one fast and conservative technique, and one exact but more computationally demanding. We then combine these two techniques into an abstraction-refinement approach, that we implement in a tool called VoTE (Verifier of Tree Ensembles). Using a couple of case studies, we recognize that sets of inputs that lead to the same system behavior can be captured precisely as hyperrectangles, which enables tractable enumeration of input-output mappings when the input dimension is low. Tree ensembles with a high-dimensional input domain, however, seems generally difficult to verify. In some cases though, conservative approximations of input-output mappings can greatly improve performance. This is demonstrated in a digit recognition case study, where we assess the robustness of classifiers when confronted with additive noise.

Artificial intelligence, or AI, now affects the day-to-day life of almost everyone on the planet, and continues to be a perennial hot topic in the news. This book presents the proceedings of ECAI 2023, the 26th European Conference on Artificial Intelligence, and of PAIS 2023, the 12th Conference on Prestigious Applications of Intelligent Systems, held from 30 September to 4 October 2023 and on 3 October 2023 respectively in Kraków, Poland. Since 1974, ECAI has been the premier venue for presenting AI research in Europe, and this annual conference has become the place for researchers and practitioners of AI to discuss the latest trends and challenges in all subfields of AI, and to demonstrate innovative applications and uses of advanced AI technology. ECAI 2023 received 1896 submissions – a record number – of which 1691 were retained for review, ultimately resulting in an acceptance rate of 23%. The 390 papers included here, cover topics including machine learning, natural language processing, multi agent systems, and vision and knowledge representation and reasoning. PAIS 2023 received 17 submissions, of which 10 were accepted after a rigorous review process. Those 10 papers cover topics ranging from fostering better working environments, behavior modeling and citizen science to large language models and neuro-symbolic applications, and are also included here. Presenting a comprehensive overview of current research and developments in AI, the book will be of interest to all those working in the field.

Formal Methods in Computer-Aided Design (FMCAD) is a conference series on the theory and applications of formal methods in hardware and system verification. FMCAD provides a leading forum to researchers in academia and industry for presenting and discussing ground-breaking methods, technologies, theoretical results, and tools for reasoning formally about computing systems. FMCAD covers formal aspects of computer-aided system design including verification, specification, synthesis, and testing.

This book constitutes the proceedings of the Workshops held in conjunction with SAFECOMP 2019, 38th International Conference on Computer Safety, Reliability and Security, in September 2019 in Turku, Finland. The 32 regular papers included in this volume were carefully reviewed and selected from 43 submissions; the book also contains two invited papers. The workshops included in this volume are: ASSURE 2019: 7th International Workshop on Assurance Cases for Software-Intensive Systems DECSoS 2019: 14th ERCIM/EWICS/ARTEMIS Workshop on Dependable Smart Embedded and Cyber-Physical Systems and Systems-of-Systems SASSUR 2019: 8th International Workshop on Next Generation of System Assurance Approaches for Safety-Critical Systems STRIVE 2019: Second International Workshop on Safety, securiTy, and pRivacy In automotiVe systEms WAISE 2019: Second International Workshop on Artificial Intelligence Safety Engineering

The Conference on Formal Methods in Computer-Aided Design (FMCAD) is an annual conference on the theory and applications of formal methods in hardware and system in academia and industry for presenting and discussing groundbreaking methods, technologies, theoretical results, and tools for reasoning formally about computing systems. FMCAD covers formal aspects of computer-aided system testing.

This book addresses the latest approaches to holistic Cyber-Physical System (CPS) resilience in real-world industrial applications. Ensuring the resilience of CPSs requires cross-discipline analysis and involves many challenges and open issues, including how to address evolving cyber-security threats. The book describes emerging paradigms and techniques from two main viewpoints: CPSs’ exposure to new threats, and CPSs’ potential to counteract them. Further, the chapters address topics ranging from risk modeling to threat management and mitigation. The book offers a clearly structured, highly accessible resource for a diverse readership, including graduate students, researchers and industry practitioners who are interested in evaluating and ensuring the resilience of CPSs in both the development and assessment stages.

The three-volume sets constitute the refereed proceedings of the 15th International Conference on Knowledge Science, Engineering and Management, KSEM 2022, held in Singapore, during August 6–8, 2022. The 169 full papers presented in these proceedings were carefully reviewed and selected from 498 submissions. The papers are organized in the following topical sections: Volume I:Knowledge Science with Learning and AI (KSLA) Volume II:Knowledge Engineering Research and Applications (KERA) Volume III:Knowledge Management with Optimization and Security (KMOS)

Information and communication technology is fundamentally changing the way we live and operate in cities, such as instant access to events, transportation, bookings, payments, and other services. At the same time, three “megatrends” in the automotive industry—self-driving, electrification, and advanced manufacturing technology—are enabling the design of innovative, application-specific vehicles that capitalize on city connectivity. Applications could countless; however, they also need to be safe and securely integrated into a city’s physical and digital infrastructure, and into the overall urban ecosystem. Unsettled Issues Concerning Automated Driving Services in the Smart City Infrastructure examines the current state of the industry, the developments in automated driving and robotics, and how these new urban, self-driving city applications are different. It also analyzes higher level challenges for urban applications. Ultimately, this report includes several options for sharing lessons learned among different cities and their stakeholders. Click here to access the full SAE EDGETM Research Report portfolio. https://doi.org/10.4271/EPR2021030