Security Vulnerability Detection with Enhanced Privacy Preservation for Edge Computing Using Hybrid Machine Learning Approach

Patil, Shubham Prashant (2022) Security Vulnerability Detection with Enhanced Privacy Preservation for Edge Computing Using Hybrid Machine Learning Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Edge computing, which is now a slashing method, allows for the processing and calculation of upstream data in consideration of IoT properties and downstream data with the assistance of cloud services. The primary notion of edge computing is to move calculations closer to data sources, such as edge devices or IoT nodes, by bringing cloud computing to the network’s edge. By using edge computing, services may be located close to the original data source in order to satisfy critical needs in agile connectivity, pragmatic optimization, smart or intelligent applications, reliability, and secrecy. One of the most pressing issues surrounding edge computing is the prevention of malware and other security breaches in networks. Several researchers have developed numerous ensemble approaches to network data for addressing security issues, however, these methods are unable to neutralize all modern network incursions in edge computing’s rapidly developing and changing network traffic data pattern. As a consequence of this, there is a necessity for an Edge Intrusion attack classifier Framework (EIACF) that monitors the network for potentially harmful activity. In this study, we have demonstrated different classifiers such as Random Forest (RF), XGBoost, and KNN classifiers and proposed a hybrid classifier (EIACF) with the help of ensemble learning which is combined with Infinite feature selection and PCA for detecting edge network anomalies. The experimental outcomes illustrate that the EIHCF has an accuracy of 99.33%. When compared to the findings of the prior work, these results show an improvement in performance. In our trials, we utilized NSL-KDD datasets to assess the model’s performance.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Heeney, Sean UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	19 Apr 2023 12:03
Last Modified:	19 Apr 2023 12:03
URI:	https://norma.ncirl.ie/id/eprint/6481

Actions (login required)

View Item