Intrusion Detection in Network Systems Through Hybrid Supervised and Unsupervised Machine Learning Process: A Case Study on the ISCX Dataset

Abstract

Data mining techniques play an increasing role in the intrusion detection by analyzing network data and classifying it as 'normal' or 'intrusion'. In recent years, several data mining techniques such as supervised, semi-supervised and unsupervised learning are widely used to enhance the intrusion detection. This work proposes a hybrid intrusion detection (kM-RF) which outperforms in overall, according to our experimentation, the alternative methods through the accuracy, detection rate and false alarm rate. A benchmark intrusion detection dataset (ISCX) is used to evaluate the efficiency of the kM-RF, and a deep analysis is conducted to study the impact of the importance of each feature defined in the pre-processing step.