Comparative study of conjugate gradient to optimize learning process of neural network for Intrusion Detection System (IDS)

Intrusion Detection System (IDS) is a device or software application that monitors and inspects all inbound and outbound network activities, identifies suspicious patterns that may be a network attack from someone attempting to break into or compromise a system. IDS categorize in two ways, namely misuse detection and anomaly detection. In this research, intrusion detection was done by anomaly detection. The data used is KDDCUP dataset 1999, which has 4 types of attacks, namely DoS, U2R, R2L, and Prob. Anomaly detection was built using Backpropagation algorithm optimized by Conjugate Gradient algorithm. In this paper, it was implemented and analyzed the use of CG optimization (Fletcher Reeves, Polak Ribiere, Powell Beale) in the process of backpropagation learning for IDS. Moreover, to minimize the performance of learning rate parameter, four types of line search techniques used, i.e. Brent Search, Golden Section Search, Charalambous Search and Hybrid Bisection-cubic Search. Based on the experiment results, the proposed scheme gives the best accuracy when the data is divided into two classes with a proportion of normal and intrusion data was balanced, with an average accuracy of 93.2%. Meanwhile, the multi class classification model has an average f-measure of 54.13%. The best performance was obtained by using Conjugate Gradient-Fletcher Reeves optimization method and line search method Hybrid Bisection-Cubic Search.