International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
Most of the researchers have argued that Artificial Neural Networks (ANNs) can improve the performance of Intrusion Detection Systems (IDSs). The central areas in network intrusion detection are how to build effective systems that are able to distinguish normal from intrusive traffic. In this paper, the authors have used data reduction algorithm CFS subset and four different neural networking algorithms namely multilayer perception, stochastic gradient descent, logistic regression and voted perception. All these algorithms are implemented in WEKA data mining tool to evaluate the performance.