ABSTRACT
Detection of cyber intrusions has recently piqued researchers’ interest due to recent significant advancements and impressive results in machine learning techniques in the fields of image recognition and natural language processing and speech recognition for various long-standing artificial intelligence tasks. Different machine learning algorithms for Internet of Things (IoT) intrusion detection in aerospace cyber-physical systems are presented in this chapter. The Cooja IoT simulator was utilized in our research to create high-fidelity attack data in IoT 6LoWPAN networks. The most efficient network design for all machine types is selected by analyzing multiple network topologies and network situations. The experimental results reveal that machine learning models for intrusion detection outperform traditional methods by more than 99% accuracy, efficiency, and detection rate. In addition, the suggested models may be employed in limited situations, such as IoT sensors, because of their low energy consumption and memory requirements.
