Comparative Analysis of Back propagation Algorithm Variants for Network Intrusion Detection

Abstract

increasing with the growth of hacking tools, complexity of networks and intrusions in number and severity. The intrusion detection is the process that detects possible network attacks or different security violations, abnormal activities and alerts the occurrences to network administrator. This research is focused on intrusion detection by using Multilayer Perceptron (MLP) with different algorithm of backpropagation neural network. In this research, performance of various backpropagation algorithms has been evaluated using KDDCup99 dataset. The dataset has been preprocessed to be made suitable for neural network input and the input set and target set are separated. The modified dataset has been used to evaluate the performance of BFGS Quasi-Newton, Levenberg-Marquardt, Gradient Descent with Adaptive lr backpropagation algorithm. Different performance parameters such as mean square error, attack detection rate, recall rate, precision rate, epochs has been used for the algorithm comparison. Based on the evaluation results, the research purposes Levenberg-Marquardt backpropagation algorithm to be the best performing and efficient algorithm for the network intrusion detection for KDDCup dataset. Different classes of attacks have been also determined comparing the output values obtained with the target set.