MULTI-LAYER ATTACK DETECTION MODEL FOR BLUETOOTH-CONNECTED DEVICES IN SMART HEALTHCARE SYSTEM

Abstract

Internet of Things (IoT) is an interconnected network of heterogeneous things through the Internet. The current and next generation of smart healthcare systems are dependent on Internet of Medical things (IoMT) devices (e.g, smart wireless medical sensors). In the current interconnected world, Bluetooth technology plays a vital role in shortrange of communication due to its less resource consumption due to its flexibility and low resource consumption which suits the IoMT architecture and design. Smart health system present an ever-expanding attack surface due to the continuous adoption of a broad variety of Internet of Medical Things (IoMT) devices and applications. IoMT is a common approach to smart city solutions that deliver long-term benefits to critical infrastructure such as smart healthcare. As smart healthcare applications rely on distributed control optimization, artificial intelligence (AI), and in particular, deep learning (DL), offers an effective approach to mitigate cyber-attacks. In this thesis we presents a decentralized, predictive DL-based process to autonomously detect and block malicious traffic and provide end-to-end defense against network attacks in IoMT devices. Furthermore, we provide the BlueTack dataset for Bluetooth-based attacks against IoMT networks. To the best of our knowledge this is the first intrusion detection dataset for the Bluetooth Classic and Bluetooth Low Energy (BLE). Using the BlueTack dataset, we devise a multi-layer intrusion detection method that uses deep-learning techniques. Then, we propose a decentralized architecture for deploying this IDS on the edge device of a smart-healthcare system that may be deployed in a smart city. The presented multi-layer intrusion detection models achieve performance in the range of 97%-99.5% based on the F1 scores.