Improving Detection Rate of the Network Intrusion Detection System Based on Wrapper Feature Selection Approach
Regarding the security of computer systems, the intrusion detection systems (IDSs) are essential components for the detection of attacks at the early stage. They monitor and analyze network traffics, looking for abnormal behaviors or attack signatures to detect intrusions in real time. A major drawback of the IDS is their inability to provide adequate sensitivity and accuracy, coupled with their failure in processing enormous data. The issue of classification time is greatly reduced with the IDS through feature selection. In this paper, a new feature selection algorithm based on Firefly Algorithm (FA) is proposed. In addition, the naïve bayesian classifier is used to discriminate attack behaviour from normal behaviour in the network traffic. The FA selects the discriminating features from NSL-KDD dataset. The performance of the IDS in the detection of attacks was enhanced by the proposed model and compare with other models.