Paper Contents
Abstract
As more and more devices connect to the Internet of Things (IoT), maintaining the confidentiality and authenticity of the data stored within these networks has become of the utmost importance. The purpose of this study is to investigate the feasibility of using mobile cloud infrastructures in conjunction with edge computing as a strategy to improve the safety of Internet of Things (IoT) systems. The inherent nature of edge computing allows it to drastically lower the latency and bandwidth overheads of traditional cloud-centric Internet of Things models, which paves the way for real-time anomaly detection to become a reality. The implementation of One-Class Support Vector Machine (1CSVM), a machine learning technique specialised for anomaly detection in cases when aberrant data is scarce and difficult to discriminate, lies at the heart of our methodology. We present a comprehensive analysis of how 1CSVM can be effectively integrated within the edge-mobile cloud paradigm to detect and mitigate threats at the data generation source, thereby reducing the risks associated with transmitting potentially compromised data to centralised cloud repositories. This is accomplished by detecting and mitigating threats at the data generation source. Our findings highlight the promise that this hybrid strategy holds for improving the security of the internet of things (IoT), offering both theoretical insights and practical instructions for its implementation.
Copyright
Copyright © 2023 Suneetra Chatterjee. This is an open access article distributed under the Creative Commons Attribution License.
