Experiments on detection of Denial of Service attacks using ensemble of classifiers

Abstract

Malicious users of the internet can launch Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks with the intent of making the throughput of a network next to none. As the types and number of users of the internet increases, the requirement of an effective Intrusion Detection System(IDS) to detect these attacks also increases. Different techniques such as data mining and pattern recognition are being used to design IDS. One of the major challenges faced while designing IDSs is maximizing the accuracy of detection. To address this issue, this paper has used Ensemble of classifiers approach where each class uses different learning paradigm. The classifiers used for experimentation are Naive Bayesian(NB), Bayesian Network(BN), Sequential Minimal Optimization(SMO), J48(C4.5) and Reduced Error Pruning Tree(REPTree). Experimental results show improvements in detection accuracy for Denial of Service attacks.