Abstract
Digital healthcare is a composite infrastructure of networking entities that includes the Internet of Medical Things (IoMT)-based Cyber-Physical Systems (CPS), base stations, services provider, and other concerned components. In the recent decade, it has been noted that the demand for this emerging technology is gradually increased with cost-effective results. Although this technology offers extraordinary results, but at the same time, it also offers multifarious security perils that need to be handled effectively to preserve the trust among all engaged stakeholders. For this, the literature proposes several authentications and data preservation schemes, but somehow they fail to tackle this issue with effectual results. Keeping in view, these constraints, in this paper, we proposed a lightweight authentication and data preservation scheme for IoT based-CPS utilizing deep learning (DL) to facilitate decentralized authentication among legal devices. With decentralized authentication, we have depreciated the validation latency among pairing devices followed by improved communication statistics. Moreover, the experimental results were compared with the benchmark models to acknowledge the significance of our model. During the evaluation phase, the proposed model reveals incredible advancement in terms of comparative parameters in comparison with benchmark models.
Highlights
Internet of Medical Things (IoMT)-based patient wearable devices and gadgets are employed in an open atmosphere with a radio communication infrastructure, which puts them a risk of new security threats
We explain the detail of hybrid Deep Learning techniques for privacy using homomorphic encryption. In response to these challenges, in this paper, we propose a hybrid lightweight authentication scheme, which is basically designed from two different attributes such as the supervised machine learning (SML) technique and the Cryptographic Parameter Based Encryption and Decryption (CPBED) model to ensure the validation of legal devices followed by secure data transmission in the IoMT-based Cyber-Physical Systems (CPS)
We propose a Proof of Improved consensus algorithm designed for blockchain to validate the blocks before they are committed to the ledger; The design of a deep learning-based secure model to identify honest miners and restrict malicious miners; We present a complete working solution for the integration of the proposed consensus algorithm with the Ethereum Framework; A comparative analysis of the existing consensus and the proposed consensus protocol is presented; The design of a novel algorithm is added in order to secure the proposed model
Summary
IoMT-based patient wearable devices and gadgets are employed in an open atmosphere with a radio communication infrastructure, which puts them a risk of new security threats It is patient wearable devices that are susceptible to security risks, but their collected and transmitted data are at risk during the communication process; the whole ecosystem needs to be shielded against internal and external threats [1]. Even though many experts have worked in this field to alleviate the known vulnerabilities and threats, over time these authentication models become susceptible to external and internal threats as the adversaries continually try to tamper and hijack them This domain is still open to new authentication schemes that could help to promote the validation process with better communication attributes.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
