Deep Learning-Based Fog-Cloud Approach Intrusion Detection System in IoMT

The Internet of Medical Things (IoMT) creates an interconnected environment linking humans, devices, sensors, and systems, enhancing healthcare services through advanced technologies. Nonetheless, these IoMT devices are susceptible to cyberattacks, which can endanger patient safety and healthcare services. To identify and mitigate cyberattacks in IoMT, techniques such as threat intelligence, log monitoring, and intrusion detection systems are employed. As attackers evolve their strategies, there is a growing trend towards leveraging artificial intelligence to achieve more predictive and accurate attack detection. Since IoMT devices are inherently low-power, they require minimal computing resources. Existing intrusion detection systems are generally trained in the cloud, which poses considerable privacy risks to user data and increases the time needed for detecting intrusions. Fog computing provides services using edge computing resources to overcome the limitations of cloud-based centralized systems. Therefore, we propose a framework for detecting cyberattacks early in IoMT environment, driven by deep learning and a fog-cloud approach. Our model employs RNN-based architectures, consisting of a Bidirectional SimpleRNN for binary intrusion detection and a GRU model for multiclass intrusion detection. Additionally, we introduce a system for implementing the proposed solution using IoMT-based Software as a Service (SaaS) in the fog and Infrastructure as a Service (IaaS) in the cloud. The proposed approach was assessed using the CICIoMT2024 and ECU_IoHT datasets. The results indicate that this method surpasses existing models, achieving an accuracy of 99.04% and 95.73% for binary and multi-class classification respectively, while also enhancing performance by decreasing time complexity.