This paper presents a comprehensive survey of Intelligent Internet of Things (IIoT), focusing on its applications, security, privacy, and future directions. IIoT integrates artificial intelligence (AI) with IoT to create a new networking paradigm that significantly transforms businesses and industrial domains. The paper explores the roles of IIoT in various application domains, including smart healthcare, smart cities, smart transportation, and smart industries. It investigates important security issues in IIoT networks, such as network attacks, confidentiality, integrity, and intrusion, along with potential countermeasures. Privacy issues in IIoT networks are also discussed, including data, location, and model privacy leakage. The paper outlines several key challenges and highlights potential research directions in this important area. The paper discusses the integration of AI techniques, including machine learning (ML), deep learning (DL), reinforcement learning (RL), and federated learning (FL), in IIoT systems. It provides an in-depth look at the cutting-edge developments in these technologies within the context of IoT systems. The paper also explores the concepts and prospects of integrating these technologies, highlighting their potential for improving IoT applications. The paper discusses the applications of IIoT in various domains, including smart healthcare, smart cities, smart transportation, and smart industries. In smart healthcare, IIoT is used for patient monitoring, ambient assisted living (AAL), and COVID-19 detection. In smart cities, IIoT is used for smart grids and water management. In smart transportation, IIoT is used for real-time decision-making and efficient resource management. In smart industries, IIoT is used for predictive maintenance and process optimization. The paper also discusses the security and privacy challenges in IIoT systems, including network attacks, confidentiality, integrity, and intrusion. It highlights the potential of ML/DL-based models for addressing these challenges, as well as the role of FL in preserving privacy in IIoT systems. The paper concludes with a discussion of future research directions in IIoT, emphasizing the need for multidisciplinary research to address the challenges of security, privacy, and scalability in IIoT systems.This paper presents a comprehensive survey of Intelligent Internet of Things (IIoT), focusing on its applications, security, privacy, and future directions. IIoT integrates artificial intelligence (AI) with IoT to create a new networking paradigm that significantly transforms businesses and industrial domains. The paper explores the roles of IIoT in various application domains, including smart healthcare, smart cities, smart transportation, and smart industries. It investigates important security issues in IIoT networks, such as network attacks, confidentiality, integrity, and intrusion, along with potential countermeasures. Privacy issues in IIoT networks are also discussed, including data, location, and model privacy leakage. The paper outlines several key challenges and highlights potential research directions in this important area. The paper discusses the integration of AI techniques, including machine learning (ML), deep learning (DL), reinforcement learning (RL), and federated learning (FL), in IIoT systems. It provides an in-depth look at the cutting-edge developments in these technologies within the context of IoT systems. The paper also explores the concepts and prospects of integrating these technologies, highlighting their potential for improving IoT applications. The paper discusses the applications of IIoT in various domains, including smart healthcare, smart cities, smart transportation, and smart industries. In smart healthcare, IIoT is used for patient monitoring, ambient assisted living (AAL), and COVID-19 detection. In smart cities, IIoT is used for smart grids and water management. In smart transportation, IIoT is used for real-time decision-making and efficient resource management. In smart industries, IIoT is used for predictive maintenance and process optimization. The paper also discusses the security and privacy challenges in IIoT systems, including network attacks, confidentiality, integrity, and intrusion. It highlights the potential of ML/DL-based models for addressing these challenges, as well as the role of FL in preserving privacy in IIoT systems. The paper concludes with a discussion of future research directions in IIoT, emphasizing the need for multidisciplinary research to address the challenges of security, privacy, and scalability in IIoT systems.