Applying Artificial Neural Network and eXtended Classifier System for Network Intrusion Detection

Due to increasing incidents of cyber attacks, building effective intrusion detection systems are essential for protecting information systems security, and yet it remains an elusive goal and a great challenge. Current intrusion detection systems (IDS) examine all data features to detect intrusion or misuse patterns. Some of the features may be redundant or low importance during detection process. The purpose of this study is to identify important input features in building IDS to gain better detection rate (DR). By that, two stages are proposed for designing intrusion detection system. In the first phase, we proposed filtering process for a set of features to combine best set of features for each type of network attacks that implemented by using Artificial Neural Network (ANN). Next, we design an IDS using eXtended Classifier System (XCS) with internal modification for classifier generator to gain better detection rate. In the experiments, we choose KDD 99 as a dataset to train and examine the proposed work. From experiment results, XCS with its modifications achieves a promised performance compared with other systems for detecting intrusions