Evolutionary Approach for Network Anomaly Detection Using Effective Classification

Intrusion Detection Systems (IDS) have become a necessary component of the computer and information security framework. Due to the increase in unauthorized access and stealing of internet resources, internet security has become a very significant issue. Network anomalies in particular can cause many potential problems. This work discusses about the ways of implementing Evolutionary Approach for Network based Anomaly Detection Systems using Effective Classification. It involves characterizing the network traffic and detecting intrusion through observation of deviation from normal behavior patterns. This work aims at providing a potential solution to the problem of Network intrusion by using effective classification technique Support Vector Machines, Evolutionary approaches namely genetic algorithm(GA) and Particle Swarm Optimization (PSO). These evolutionary approaches are used for feature selection and SVM is used for classification. We tested this technique using KDD Cup99 dataset, and analyzed its performance. The experimental results show that the PSO-SVM is an effective approach in network intrusion detection.