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.

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.

It is common wisdom that gathering a variety of views and inputs improves the process of decision making, and, indeed, underpins a democratic society. Dubbed “ensemble learning” by researchers in computational intelligence and machine learning, it is known to improve a decision system’s robustness and accuracy. Now, fresh developments are allowing researchers to unleash the power of ensemble learning in an increasing range of real-world applications. Ensemble learning algorithms such as “boosting” and “random forest” facilitate solutions to key computational issues such as face recognition and are now being applied in areas as diverse as object tracking and bioinformatics. Responding to a shortage of literature dedicated to the topic, this volume offers comprehensive coverage of state-of-the-art ensemble learning techniques, including the random forest skeleton tracking algorithm in the Xbox Kinect sensor, which bypasses the need for game controllers. At once a solid theoretical study and a practical guide, the volume is a windfall for researchers and practitioners alike.

This state-of-the-art monograph presents a coherent survey of a variety of methods and systems for formal hardware verification. It emphasizes the presentation of approaches that have matured into tools and systems usable for the actual verification of nontrivial circuits. All in all, the book is a representative and well-structured survey on the success and future potential of formal methods in proving the correctness of circuits. The various chapters describe the respective approaches supplying theoretical foundations as well as taking into account the application viewpoint. By applying all methods and systems presented to the same set of IFIP WG10.5 hardware verification examples, a valuable and fair analysis of the strenghts and weaknesses of the various approaches is given.

Introduction to abstract interpretation, with examples of applications to the semantics, specification, verification, and static analysis of computer programs. Formal methods are mathematically rigorous techniques for the specification, development, manipulation, and verification of safe, robust, and secure software and hardware systems. Abstract interpretation is a unifying theory of formal methods that proposes a general methodology for proving the correctness of computing systems, based on their semantics. The concepts of abstract interpretation underlie such software tools as compilers, type systems, and security protocol analyzers. This book provides an introduction to the theory and practice of abstract interpretation, offering examples of applications to semantics, specification, verification, and static analysis of programming languages with emphasis on calculational design. The book covers all necessary computer science and mathematical concepts--including most of the logic, order, linear, fixpoint, and discrete mathematics frequently used in computer science--in separate chapters before they are used in the text. Each chapter offers exercises and selected solutions. Chapter topics include syntax, parsing, trace semantics, properties and their abstraction, fixpoints and their abstractions, reachability semantics, abstract domain and abstract interpreter, specification and verification, effective fixpoint approximation, relational static analysis, and symbolic static analysis. The main applications covered include program semantics, program specification and verification, program dynamic and static analysis of numerical properties and of such symbolic properties as dataflow analysis, software model checking, pointer analysis, dependency, and typing (both for forward and backward analysis), and their combinations. Principles of Abstract Interpretation is suitable for classroom use at the graduate level and as a reference for researchers and practitioners.

Safety and Reliability of Complex Engineered Systems contains the Proceedings of the 25th European Safety and Reliability Conference, ESREL 2015, held 7-10 September 2015 in Zurich, Switzerland. It includes about 570 papers accepted for presentation at the conference. These contributions focus on theories and methods in the area of risk, safety and