Organised by University of Rome 'La Sapienza', Italy, Wessex Institute of Technology, UK.

The history of robotics and artificial intelligence in many ways is also the history of humanity’s attempts to control such technologies. From the Golem of Prague to the military robots of modernity, the debate continues as to what degree of independence such entities should have and how to make sure that they do not turn on us, its inventors. Numerous recent advancements in all aspects of research, development and deployment of intelligent systems are well publicized but safety and security issues related to AI are rarely addressed. This book is proposed to mitigate this fundamental problem. It is comprised of chapters from leading AI Safety researchers addressing different aspects of the AI control problem as it relates to the development of safe and secure artificial intelligence. The book is the first edited volume dedicated to addressing challenges of constructing safe and secure advanced machine intelligence. The chapters vary in length and technical content from broad interest opinion essays to highly formalized algorithmic approaches to specific problems. All chapters are self-contained and could be read in any order or skipped without a loss of comprehension.

A new approach to safety, based on systems thinking, that is more effective, less costly, and easier to use than current techniques. Engineering has experienced a technological revolution, but the basic engineering techniques applied in safety and reliability engineering, created in a simpler, analog world, have changed very little over the years. In this groundbreaking book, Nancy Leveson proposes a new approach to safety—more suited to today's complex, sociotechnical, software-intensive world—based on modern systems thinking and systems theory. Revisiting and updating ideas pioneered by 1950s aerospace engineers in their System Safety concept, and testing her new model extensively on real-world examples, Leveson has created a new approach to safety that is more effective, less expensive, and easier to use than current techniques. Arguing that traditional models of causality are inadequate, Leveson presents a new, extended model of causation (Systems-Theoretic Accident Model and Processes, or STAMP), then shows how the new model can be used to create techniques for system safety engineering, including accident analysis, hazard analysis, system design, safety in operations, and management of safety-critical systems. She applies the new techniques to real-world events including the friendly-fire loss of a U.S. Blackhawk helicopter in the first Gulf War; the Vioxx recall; the U.S. Navy SUBSAFE program; and the bacterial contamination of a public water supply in a Canadian town. Leveson's approach is relevant even beyond safety engineering, offering techniques for “reengineering” any large sociotechnical system to improve safety and manage risk.

We all know that safety should be an integral part of the systems that we build and operate. The public demands that they are protected from accidents, yet industry and government do not always know how to reach this common goal. This book gives engineers and managers working in companies and governments around the world a pragmatic and reasonable approach to system safety and risk assessment techniques. It explains in easy-to-understand language how to design workable safety management systems and implement tested solutions immediately. The book is intended for working engineers who know that they need to build safe systems, but aren’t sure where to start. To make it easy to get started quickly, it includes numerous real-life engineering examples. The book’s many practical tips and best practices explain not only how to prevent accidents, but also how to build safety into systems at a sensible price. The book also includes numerous case studies from real disasters that describe what went wrong and the lessons learned. See What’s New in the Second Edition: New chapter on developing government safety oversight programs and regulations, including designing and setting up a new safety regulatory body, developing safety regulatory oversight functions and governance, developing safety regulations, and how to avoid common mistakes in government oversight Significantly expanded chapter on safety management systems, with many practical applications from around the world and information about designing and building robust safety management systems, auditing them, gaining internal support, and creating a safety culture New and expanded case studies and "Notes from Nick’s Files" (examples of practical applications from the author’s extensive experience) Increased international focus on world-leading practices from multiple industries with practical examples, common mistakes to avoid, and new thinking about how to build sustainable safety management systems New material on safety culture, developing leading safety performance indicators, safety maturity model, auditing safety management systems, and setting up a safety knowledge management system

"Organised by Wessex Institute of Technology, UK; University of Antwerp, Belgium; University of Rome 'La Sapienza', Italy" - prelim.

Safety has traditionally been defined as a condition where the number of adverse outcomes was as low as possible (Safety-I). From a Safety-I perspective, the purpose of safety management is to make sure that the number of accidents and incidents is kept as low as possible, or as low as is reasonably practicable. This means that safety management must start from the manifestations of the absence of safety and that - paradoxically - safety is measured by counting the number of cases where it fails rather than by the number of cases where it succeeds. This unavoidably leads to a reactive approach based on responding to what goes wrong or what is identified as a risk - as something that could go wrong. Focusing on what goes right, rather than on what goes wrong, changes the definition of safety from ’avoiding that something goes wrong’ to ’ensuring that everything goes right’. More precisely, Safety-II is the ability to succeed under varying conditions, so that the number of intended and acceptable outcomes is as high as possible. From a Safety-II perspective, the purpose of safety management is to ensure that as much as possible goes right, in the sense that everyday work achieves its objectives. This means that safety is managed by what it achieves (successes, things that go right), and that likewise it is measured by counting the number of cases where things go right. In order to do this, safety management cannot only be reactive, it must also be proactive. But it must be proactive with regard to how actions succeed, to everyday acceptable performance, rather than with regard to how they can fail, as traditional risk analysis does. This book analyses and explains the principles behind both approaches and uses this to consider the past and future of safety management practices. The analysis makes use of common examples and cases from domains such as aviation, nuclear power production, process management and health care. The final chapters explain the theoret