As AI systems become increasingly embedded in all facets of society from healthcare and finance to transportation and public services, ensuring their safe and responsible operation has never been greater. AI safety and harm prevention encompass the principles designed to keep intelligent systems aligned with human values, resilient to misuse, and robust against failure. By proactively addressing risks such as biased outputs, security vulnerabilities, and unintended societal impacts, organizations can cultivate AI systems that are not only powerful and efficient but also trustworthy and protective of the people they are built to serve. AI Safety and Preventing Harm in AI Systems explores AI risks and trustworthiness, covering governance dimensions. This book examines the validity and security of AI systems while also addressing accountability and fairness of these systems. Covering topics such as AI systems, ethics, and AI safety, this book is an excellent resource for AI researchers, cybersecurity experts, ethicists, policymakers, industry practitioners, and graduate students.