A Study on Intrusion Detection Using Centroid-Based Classification

The ultimate goal of intrusion detection system (IDS) development is to accomplish the best possible accuracy for detection attacks. Various hybrid machine learning techniques were developed for IDS. The centroid-based classification method is a particular hybrid learning approach that highly efficient in the training and classification stages. This paper studies 60 associated papers in the period between 2010 and 2016 concentrating on developing IDS using hybrid classifiers, which 11 papers used centroid-based classification. Similar studies are compared by the algorithm used in hybrid machine learning, the dataset used, the establishment of the representative feature, the stages of pre-processing data, and evaluation methods considered. The accomplishments and limitations in developing IDSs using hybrid machine learning and centroid-based classification were presented and discussed. Several future research opportunities were provided that may encourage interested researchers to work in this area.