Cyber Attacks in the Internet of Things: AI-Driven Detection, Mathematical Modeling, and Defense Mechanisms

The unprecedented growth of the Internet of Things (IoT) has revolutionized the modern digital world by interconnecting billions of smart devices, sensors, communication systems, and cyber-physical infrastructures. From smart homes and intelligent transportation systems to healthcare monitoring, industrial automation, smart grids, and defense applications, IoT technologies have become deeply integrated into almost every aspect of human life. However, this massive connectivity and dependence on digital infrastructures have simultaneously created serious cybersecurity challenges. IoT ecosystems are increasingly vulnerable to sophisticated cyber threats such as malware propagation, ransomware attacks, botnet formation, data breaches, distributed denial-of-service (DDoS) attacks, and intelligent adversarial intrusions. The complexity, heterogeneity, and resource-constrained nature of IoT devices often render traditional cybersecurity mechanisms inadequate for ensuring reliable and resilient protection. In recent years, researchers and practitioners across the globe have recognized the urgent need for intelligent, adaptive, and mathematically rigorous cybersecurity frameworks capable of understanding and mitigating cyber threats in IoT environments. Advances in Artificial Intelligence (AI), Machine Learning (ML), deep learning, blockchain technology, network science, and mathematical modeling have opened new directions for developing predictive, autonomous, and resilient cyber-defense systems. In particular, mathematical approaches such as cyber-epidemic models, stochastic processes, optimization techniques, graph-theoretic methods, and fractional-order dynamical systems have emerged as powerful tools for analyzing cyber-attack transmission dynamics and designing effective defense strategies. This edited volume, Cyber Attacks in the Internet of Things: AI-Driven Detection, Mathematical Modeling, and Defense Mechanisms, has been conceived to provide a comprehensive interdisciplinary platform bringing together recent theoretical developments, computational methodologies, practical implementations, and real-world case studies in IoT cybersecurity. The primary objective of the book is to bridge the gap between cybersecurity engineering, artificial intelligence, and applied mathematical sciences, thereby promoting integrated approaches for securing next-generation IoT ecosystems. The chapters included in this volume highlight diverse aspects of IoT security including malware propagation modeling, AI-assisted intrusion detection systems, blockchain-enabled security architectures, anomaly detection, cyber risk assessment, optimization-based defense mechanisms, privacy preservation, and resilient cyber-defense strategies for critical infrastructures. A distinguishing feature of this book is its emphasis on the integration of AI/ML techniques with mathematical and computational modeling frameworks for understanding the dynamic behavior of cyber attacks and developing intelligent mitigation strategies. The volume includes contributions addressing both theoretical and application-oriented perspectives in areas such as Industrial IoT (IIoT), Internet of Medical Things (IoMT), smart cities, smart transportation, energy systems, cloud-edge-fog architectures, and cyber-physical systems. The book also explores emerging themes including federated learning, explainable AI for cybersecurity, lightweight cryptographic mechanisms, blockchain-assisted trust management, and adaptive cyber resilience frameworks. This volume is intended for a broad readership including researchers, academicians, cybersecurity professionals, data scientists, engineers, policymakers, and graduate students working in the domains of IoT security, artificial intelligence, data analytics, cyber-physical systems, and applied mathematics. It is our sincere hope that this book will not only serve as a valuable reference source for current developments in IoT cybersecurity but will also stimulate future research toward the development of secure, intelligent, and trustworthy digital infrastructures. The editors express their sincere gratitude to all contributing authors for sharing their valuable research contributions and insights for this volume. We are also thankful to the reviewers for their constructive comments and suggestions, which significantly helped in improving the quality and scientific rigor of the chapters. Finally, we acknowledge the support of our institutions, colleagues, and the wider research community whose continuous efforts are advancing the field of intelligent cybersecurity and secure IoT technologies. We hope that this book will contribute meaningfully toward addressing the growing cybersecurity challenges of the interconnected world and inspire innovative research at the intersection of IoT, Artificial Intelligence, and Mathematical Sciences.