Edge Intelligence Based Mitigation of False Data Injection Attack In IoMT Framework

Abstract

IoMT is a networked infrastructure comprising services, software, hardware, and medical equipment. By removing the need for in-person visits, this type of technology is improving patient experiences in other ways as well. But also significantly lowering the cost, resulting in an increase in patient care all around. Vulnerabilities in IoMT, such as false data injection, lead to data corruption and false diagnoses, which ultimately leads to severe damage to the patient. Due to the high dimensionality and dynamic nature of the data, machine learning has the potential to provide an effective solution. Therefore to safeguard the IoMT devices and protect the data integrity, this paper proposes a novel mitigation technique for false data injection using an XGBoost Machine Learning model. The model has produced an overall accuracy of 92% while classifying given data as genuine or false. A IoMT node was developed for real-time testing and validation of the proposed mitigation technique. The proposed model displays better performance and enhanced accuracy compared to similar methods.