Cyber threat detection in 6G wireless network using ensemble majority-voting classifier

Advance tools are required for securing the 6G wireless network, like an IDS (intrusion detection system), that utilizes the current ongoing technologies as machine learning, applying which can boost up the accuracy of results, which has been discussed in this paper. This paper attempts to perform a comprehensive analysis upon application of various distinct machine learning classifiers to the AWID-(II)-2019 dataset, which contains both types of traffic flows for wireless networks, i.e., normal and abnormal, to derive which classifier has the best efficiency and accuracy in detecting intrusions. This evaluation has been conducted based on certain parameters and performance evaluation metrics, based on the construction of a confusion matrix. This chapter proposed an ensemble majority-voting classifier for intrusion detection systems, to achieve the best results based on the above-mentioned performance metrics. The accuracy of the results for the proposed ensemble majority-voting classifier is 90.45%.