Analisis Klasifikasi Serangan Intrusi Menggunakan Skema HGN

Abstract

Intrusion detection is an action to monitor and analyze network traffic. In conducting monitoring and analysis, intrusion detection system should have early detection against intrusion attacks. This research uses HGN scheme to classify patterns of intrusion attacks that exist in the KDD Cup 99 dataset. This research is performed in two stages: preprocessing stage that includes the selection attributes using Information Gain Attribute Evaluation techniques, discretization using Entropy Based Discretization Supervised methods, election of training data using K-Means clustering algorithm, and processing stage as a classification process using scheme HGN. The results of the classification process is used to measure the accuracy rate, detection rate, false positive rate and true negative rate. The test result shows that the HGN scheme is very good and stable in classifying the intrusion attack patterns with accuracy rate reaches 96.27%, detection rate reaches 99.20%, true negative rate below 15.73%, while false positive rate is very low with a percentage of 0.80%.