Abstract

The Internet of Things (IoT) is a network of devices used for interconnection anddata transfer. There is a dramatic increase in IoT attacks due to the lack of securitymechanisms. The security mechanisms can be enhanced through the analysis andclassification of these attacks. The multi-class classification of IoT botnet attacks(IBA) applied here uses a high-dimensional data set. The high-dimensional data setis a challenge in the classification process due to the requirements of a high numberof computational resources. Dimensionality reduction (DR) discards irrelevantinformation while retaining the imperative bits from this high-dimensional data set.The DR technique proposed here is a classifier-based feature selection using an extratree classifier (EXT). The entropy values of features are used for the construction oftrees in EXT, which is to build a lower-dimensional space. Linear discriminantanalysis (LDA), K-nearest neighbor classifier (KNN), decision tree classifier (DTC),and random forest classifier (RFC) empirically evaluate the proposed featureselection mechanism. EXT is compared with other DR techniques like RFC andprincipal component analysis (PCA). The performance metrics of the classifiers areused to evaluate the proposed work.

Keywords

The article was added to IASJ on 2023-08-10

57 Total full text downloads since the date of addition