Document Type : Research Paper
Abstract
The Internet of Medical Things (IoMT) offers significant benefits for healthcare but faces growing cybersecurity challenges. This paper provides a holistic panorama of cyber-attacks detection systems developed recently for IoMT environment. By exploring the evolution and impact of cyber-attack versions, including Denial of Service (DoS), malware, Man-in-the-Middle (MitM), and data injection attacks; the detection approaches are categorized and examined including signature-based, anomaly-based, and hybrid-based approaches those leverage machine learning and deep learning algorithms. Then, the key distinction of detection approaches that assisted by ensemble machine learning, is highlighted to demonstrate their superior performance outcomes for securing IoMT environment through characterizing the challenges acquired to optimize in the nearest future research direction. As such, challenges of defeating the sophisticated cyber-attacks and the need to improve the existing detection approaches would provide valuable insights to researchers aiming at finding optimized cyber-defense to save operation of IoMT systems.
)
