Machine learning solutions for securing IoT-based healthcare: A Review
Kharoubi Kamir, Cherbal Sarra · 2023
The Internet of Things (IoT) has become a powerful force that is revolutionizing various fields to improve human life, including healthcare. By establishing interconnectedness among devices through network connectivity, IoT facilitates real-time data exchange, enables remote patient diagnosis, and ensures ubiquitous access. However, the exchange of sensitive patient data within healthcare IoT systems presents significant security and privacy challenges that must be addressed to achieve a secure Healthcare IoT (H-IoT) ecosystem, resilient to attacks and threats. Among these issues, there are integrity, privacy and availability of data. It highlights the pressing need for robust security measures to safeguard patient information and explores the promising role of the ML techniques in addressing these challenges. ML algorithms offer the ability to detect and prevent both known and unknown attacks at an early stage, enhancing the security of H-IoT systems. This paper provides an overview about H-IoT, its requirements in security and some existing attacks. Then, it presents ML techniques and their utilization for security. Finally, it conducts an extensive review of the contemporary solutions employed for enhancing the security of H-IoT systems during the period spanning from 2020 to 2023.