Intrusion Detection in Heterogeneous IoT Networks: A Future-based Comprehensive Study

The Internet of Things (IoT) consists of physical objects that are associated by sensors, software, and connectivity to gather data and facilitate the transfer of data. The features that define IoT designs are heterogeneity, which presents a network with different devices, protocols, and networks with differing capacities, data formats. Intrusion Detection (ID) is crucial for cybersecurity, as it provides an effective means of real-time monitoring systems and networks to respond to malicious activities, anomalies, and violations of policy from a security perspective in heterogeneous IoT. This survey examines various ID techniques, including Deep Learning (DL), Machine Learning (ML), Rule-based, and Statistical, Blockchain-enabled Intrusion Detection System (IDS) techniques for detecting intrusions. The study highlights new trends, including federated IDS, explainable Artificial Intelligence (AI), and lightweight edge security. This also discusses significant challenges that need to be tackled in order to create effective, scalable, and adaptable ID solutions for future IoT environments.