Performance comparison of intrusion detection system based anomaly detection using artificial neural network and support vector machine

This study presents a comparison of the detection accuracy of ANN and SVM on the anomaly-based IDS and uses all the features in the dataset. The experiments were performed on two algorithms using KDDCup99 dataset, preprocessing performed on datasets for normalization and scaling attributes which consist of four categories in the dataset. Artificial Neural Network managed to obtain high accuracy in all categories outperformed SVM with accuracy, DoS 92.20%, 90.60% Probe, R2L 89%, and U2R 90.80%. According to the results obtained from experiments using all the features dataset showed that ANN has better performance than SVM in attack detection accuracy.