A Hybrid Mutual Authentication Approach for Artificial Intelligence of Medical Things

Abstract

Artificial Intelligence of Medical Things (AIoMT) is a hybrid of the Internet of Medical Things (IoMT) and artificial intelligence to materialize the acquisition of real-time data via the smart wearable devices. Due to a diverse geographical environment of IoMT, secure and reliable communication among these devices is a challenging task that needs to be resolved on priority basis. For this purpose, numerous device-focused authentication approaches have been proposed in the literature, however, the problem still persists. This paper introduces an advanced, secured, and efficient solution for the IoMT by leveraging a lightweight mutual authentication scheme as well as facilitating AI-enabled Big Data analytics and predictive modeling. The proposed approach is specifically designed to establish secured communication between wearable sensing devices and servers within IoMT by exploiting the desirable features of cloud-edge paradigm. In this approach, every device needs to verify whether the requesting wearable device is legitimate or not and this process needs to be carried out prior to the actual communication. Our proposed approach employs a hybrid of Advanced Encryption Standard, i.e., AES 128-bit and Medium Access Control (MAC) for the establishment of secured communication sessions. In addition, the proposed approach utilizes real-time data collection from wearable devices, enabling predictive modeling for the early detection of health anomalies, thereby, enhancing the patient outcomes of a specific disease. This continuously adaptive approach excels in real-time decision-making, promptly alerting healthcare professionals of potential risks. Simulation results have verified that the proposed approach serves an ideal solution for the resource-constrained devices by achieving the expected level of authenticity through minimum possible communication and processing overhead. Additionally, this scheme is prune against well-known security attacks in the AIoMT infrastructures.