Design of an intrusion detection system based on distance feature using ensemble classifier

This paper focuses on designing an Intrusion Detection System(IDS), which detects the family of attack in a dataset. An IDS detects various types of malicious traffic and computer usage which cannot be detected by a conventional firewall. In this proposed work, the data is extracted from UNSW_NB15 dataset. To identify the data cluster centers, the k means algorithm is used. A new and one dimensional distance based feature is used to represent each data sample. Following this, an ensemble classifier is used to classify the data. Our algorithm would classify five families of attack viz., Normal, Probe, DOS, U2R and R2L. For each and every classifier output, Training state, Performance, Error histogram, Regression Fit are plotted.