Machine Learning for Healthcare-IoT Security: A Review and Risk Mitigation

Abstract

The Healthcare Internet-of-Things (H-IoT), commonly known as Digital Healthcare, is a datadriven infrastructure that highly relies on smart sensing devices (i.e., blood pressure monitors, temperature sensors, etc.) for faster response time, treatments, and diagnosis. However, with the evolving cyber threat landscape, IoT devices have become more vulnerable to the broader risk surface (e.g., risks associated with generative AI, 5G-IoT, etc.), which, if exploited, may lead to data breaches, unauthorized access, and lack of command and control and potential harm. This paper reviews the fundamentals of healthcare IoT, its privacy, and data security challenges associated with machine learning and H-IoT devices. The paper further emphasizes the importance of monitoring healthcare IoT layers such as perception, network, cloud, and application. Detecting and responding to anomalies involves various cyber-attacks and protocols such as Wi-Fi 6, Narrowband Internet of Things (NB-IoT), Bluetooth, ZigBee, LoRa, and 5G New Radio (5G NR). A robust authentication mechanism based on machine learning and deep learning techniques is required to protect and mitigate H-IoT devices from increasing cybersecurity vulnerabilities. Hence, in this review paper, security and privacy challenges and risk mitigation strategies for building resilience in H-IoT are explored and reported.

Securing industry 5.0 using 6σ CYBERNETIC framework

“…Emerging cyber threats, IT/OT risk mitigation, auditing, compliance, cyber resilience, cyber laws. [15] Demonstrates various cyber-attacks in Healthcare-IoT (H-IoT) impacting the security and privacy domains. The research also provides potential risk mitigation strategies in H-IoT using AI/ML techniques.…”

“…Industry 5.0 facilitates the seamless integration of cyber and physical domains within manufacturing ecosystems, however, with the increased connectivity in a plant and/or between plants this widens the cyberphysical system attack surface for potential exploitation [3,15,16,17] causing enormous damages to the manufacturing system [18,19,20,21,22,23,24,25]. It is just a matter of time before the IoT turns into Ransomware of Things (RoT) [26], the advanced connectivity and denser network infrastructure create new openings for probable exploitation.…”

Cybersecurity for Sustainable Smart Healthcare: State of the Art, Taxonomy, Mechanisms, and Essential Roles

“…Intrusion detection systems have three components: information sources, analyses, and responses. Data from information sources are used in the analysis component to identify anomalies, and when an anomaly is detected, a response is initiated [167]. Intrusion detection systems can be network-based, which monitors data packets across the smart healthcare network for malicious activity, or host-based, which monitors all activities occurring within IoMT devices, servers, databases, and other system components [92].…”