Machine Learning and Deep Learning Methods for Intrusion Detection Systems in IoMT: A survey

The integration of healthcare-related sensors and devices into IoT has resulted in the evolution of the IoMT (Internet of Medical Things). IoMT that can be viewed as an improvement and investment in order to meet patients' needs more efficiently and effectively. It is progressively replacing traditional healthcare systems, particularly after the worldwide impact of COVID. IoMT devices have enabled real time monitoring in the healthcare field, allowing physicians to provide superior care while also keeping patients safe. As IoMT applications have evolved, the variety and volume of security threats and attacks including routing attacks and DoS (Denial of Service), for these systems have increased, necessitating specific efforts to study intrusion detection systems (IDSs) for IoMT systems. However, IDSs are generally too resource intensive to be managed by small IoMT devices, due to their limited processing resources and energy. In this regard, machine learning and deep learning approaches are the most suitable detection and control techniques for IoMT device-generated attacks. The purpose of this research is to present various methods for detecting attacks in the IoMT system. Furthermore, we review, compare, and analyze different machine learning (ML) and deep learning (DL) based mechanisms proposed to prevent and detect IoMT network attacks, emphasizing the proposed methods, performances, and limitations. Based on a comprehensive analysis of current defensive security measures, this work identifies potential open research related challenges and orientations for the actual design of those systems for IoMT networks, that may guide further research in this field. © 2022 IEEE.

Federated Transfer Learning-Based IDS for the Internet of Medical Things (IoMT)

The Internet of Medical Things (IoMT) is a set of medical devices and applications that connect to healthcare systems through the Internet. Those devices are equipped with communication technologies that allow them to communicate with each other and the Internet. Reliance on the IoMT is increasing with the increase in epidemics and chronic diseases such as COVID-19 and diabetes;with the increase in the number of IoMT users and the need for electronic data sharing and virtual services, cyberattacks in the healthcare sector for accessing confidential patient data has been increasing in the recent years. The healthcare applications and their infrastructures have special requirements for handling sensitive users' data and the need for high availability. Therefore, securing healthcare applications and data has attracted special attention from both industry and researchers. In this paper, we propose a Federated Transfer Learning-based Intrusion Detection System (IDS) to secure the patient's healthcare-connected devices. The model uses Deep Neural Network (DNN) algorithm for training the network and transferring the knowledge from the connected edge models to build an aggregated global model and customizing it for each one of the connected edge devices without exposing data privacy. CICIDS2017 dataset has been used to evaluate the performance in terms of accuracy, detection rate, and average training time. In addition to preserving data privacy of edge devices and achieving better performance, our comparison indicates that the proposed model can be generalized better and learns incrementally compared to other baseline ML/DL algorithms used in the traditional centralized learning schemes. © 2021 IEEE.