Survey of Machine Learning Based Intrusion Detection Methods for Internet of Medical Things

The internet of medical things (IoMT) allows the collection of physiological data using sensors, then their transmission to remote servers, which allows physicians and health professionals to analyze these data continuously and permanently and detect disease at an early stage. However, the use of wireless communication to transfer data exposes it to cyberattacks, and the sensitive and private nature of this data may represent a prime interest for attackers. Using traditional security methods on devices with limited storage and computing capacity is ineffective. On the other hand, using machine learning for intrusion detection can provide an adapted security response to the requirements of IoMT systems. In this context, a comprehensive survey on how machine learning (ML)-based intrusion detection systems address security and privacy issues in IoMT systems is performed. For this purpose, the generic three-layer architecture of IoMT and the security requirement of IoMT systems are provided. Then the various threats that can affect IoMT security are presented, and the advantages, disadvantages, methods, and datasets used in each solution based on ML are identified. Finally, some challenges and limitations of applying ML on each layer of IoMT are discussed, which can serve as a future research direction.