Cross-breed type Bayesian network based intrusion detection system (CBNIDS)

Modern day internet is victimizer of the cynical network attacks due to excessive usage and massive connectivity demands. Machine learning is an efficient approach to prevent the intrusion and classify the network attacks. This study highlights the combined power of filter approaches in intrusion detection framework. Feature selection technique removes the redundant features and builds a time consuming better-performed intrusion detector framework. This study presents a cross-breed type feature selection approach using duo filter schemes for intrusion detection. In this framework feature selection technique eliminate the irrelevant features to reduce the time complexity and build a better model to predict the result with a greater accuracy and Bayesian network based classification model has been built up to predict the types of attacks. The experiment shows that the proposed framework exhibits a superior overall performance in terms of accuracy which is 97.2746% and keeps the false positive rate at a lower rate of 0.008. The model shows better performance in terms of accuracy than other leading state-of-the-arts frameworks like Boosted DT, Hidden NB, KNN and Markov chain. The NSL-KDD is used as benchmark data set with Weka library functions in the experimental setup.