Chamberlain, RogerDutta, AshutoshJain, RajOttley, AlvittaZhang, NingGhubaish, Ali Hussain A2024-07-252024-07-252024-08-15https://hdl.handle.net/20.500.14154/72699This dissertation develops a multifaceted security framework tailored for 5G-enabled real-time Internet of medical things (IoMT) systems to significantly enhance the security infrastructure within healthcare environments. The framework pivots around three core technological advancements: the development of the light feature engineering based on the mean decrease in accuracy (LEMDA), the construction of a 5G testbed that serves as a distributed intrusion detection system (IDS), and the implementation of a hybrid deep reinforcement learning (HDRL) method. LEMDA represents a breakthrough in data processing for IoMT systems. By intelligently reducing data complexity, LEMDA enhances the speed and accuracy of threat detection mechanisms, which is crucial for handling the immense volumes of data generated in healthcare settings. This method speeds up the detection process and ensures that essential data nuances are not lost, thereby maintaining high precision in threat identification. Establishing the 5G testbed introduces a novel approach to distributed IDS. This testbed leverages the latest in 5G and multi-access edge computing (MEC) technologies to distribute the processing load, thereby enhancing the overall resilience and efficiency of the network. This strategic distribution also helps overcome traditional challenges associated with centralized systems, such as scalability issues and vulnerability to single points of failure. Furthermore, this initiative has led to creating a new dataset specifically designed to support the development of IDS methodologies congruent with the architectures of 5G and MEC. This dataset is a valuable resource for researchers across both academic and industrial spheres, facilitating the advancement of tailored intrusion detection strategies. Lastly, the HDRL method integrates deep learning and reinforcement learning techniques tailored to harness network and host data for improved threat detection. This innovative approach dynamically adapts to evolving threat landscapes, reducing the need for constant human supervision and frequent retraining. The HDRL method showcases a significant enhancement in threat detection efficacy, setting new benchmarks in the field. In addition to these primary contributions, the dissertation delves into creating comprehensive datasets through the EHMS testbed and reviews current IoMT security measures and attack techniques. These endeavors provide a holistic view of the security landscape and inform the development of the proposed security framework.140en-USIDSAI-Based Security FrameworkNetwork SecurityLEMDAHDRL-IDSThesis