An AI-Enabled Hybrid Lightweight Authentication Scheme for Intelligent IoMT Based Cyber-Physical Systems

In the era of smart healthcare, Internet of Medical Things-based Cyber-Physical Systems (IoMT-based-CPS) play an important role in acquiring, evaluating, monitoring, tracking, and prescribing patients ubiquitously. For these applications, trustworthy authentication and unassailable communication are the most noteworthy impediments to be considered to attain the trust of patients, healthcare experts, nursing staff, pharmacologists, and other involved commodities. To address these security concerns, in this paper, we present a lightweight hybrid authentication, data privacy and preservation model that is constituted from supervised machine learning (SML) algorithm and a Cryptographic Parameter Based Encryption and Decryption (CPBE&D) algorithm to guarantee the authentication of legitimate IoMT-based-CPS accompanied by encrypted data transmission over the wireless communication channel. To accomplish promising results, we have facilitated a decentralized verification and authentication among legitimate IoMT-based-CPS in the network with an objective to reduce the authentication time, computation cost, and communication overhead with the assistance of the SML algorithm to predicate and forward the authentication parameters of these devices to the next concerned trusted authority when a patient is moving from one hospital (region) to another hospital (region). During the simulation results analysis, SML and CPBE&D authentication scheme demonstrated impressive security features in terms of cost-effective authentication throughout the legitimate patient wearable IoMT-based-CPS validation process, accompanied by profitable communication metrics in the comparison of predecessor works.