Machine Learning for Healthcare-IoT Security: A Review and Risk Mitigation
Mirza Akhi Khatun, Sanober Farheen Memon, Ciarán Eising, Lubna Luxmi Dhirani
Abstract
This paper reviews the Internet of Things (IoT) in healthcare, also known as Healthcare-IoT (H-IoT), and its security and privacy challenges. Specifically, smartwatches, blood pressure sensors, and temperature sensors are discussed as IoT devices that pose vulnerabilities. Several risks may arise, such as data breaches, unauthorized access, and potential patient harm. This review explores data security challenges associated with machine learning and H-IoT. Additionally, it emphasizes the importance of monitoring healthcare IoT layers such as perception, network, cloud, and application layers. Detecting and responding to anomalies involve a wide range of cyber threats and attacks, as well as protocols such asWi-Fi 6, Narrowband Internet of Things (NB-IoT), Bluetooth, ZigBee, LoRa, and 5G New Radio (5G NR). Hence, to protect and mitigate H-IoT devices from the increasing cyber threat landscape, a robust authentication mechanism based on machine learning and deep learning techniques is required. Overall, this paper reviews the security and privacy challenges in healthcare IoT and discusses risk mitigation strategies for building cyber resilience in H-IoT.