Experiments on Detection of Denial of Service Attacks using Bayesian Network Classifier

Denial of Service (DoS) and Distributed Denial of Service (DDoS) attack exhausts the resources of server/service and makes it unavailable for legitimate users. It can result in huge loss of money. With increasing use of online services and attacks on these services, the necessity of Intrusion Detection System (IDS) for detection of DoS/DDoS attacks has also marked by organizations. Different techniques such as data mining, neural network, genetic algorithms, pattern recognition are being used to design IDS. This paper evaluates variation in performance of Bayesian Network classifier for intrusion detection when used in combination with different data pre-processing and feature selection methods. Experimental results prove that accuracy of Bayesian Network classifier is improved and performs better than other classifiers when used in combination with Feature Selection and data pre-processing methods. Keywords-Bayesian Network, Feature selection, Intrusion Detection System, Denial of Service Attack