Paper #5

A Comparative Study of Data Mining Algorithms for High Detection Rate in Intrusion Detection System

Nabeela Ashraf, Waqar Ahmad and Rehan Ashraf

Abstract: Due to the fast growth and tradition of the internet over the last decades, the network security problems are increasing vigorously. Humans can not handle the speed of processes and the huge amount of data required to handle network anomalies. Therefore, it needs substantial automation in both speed and accuracy. Intrusion Detection System is one of the approaches to recognize illegal access and rare attacks to secure networks. In this proposed paper, Naive Bayes, J48 and Random Forest classifiers are compared to compute the detection rate and accuracy of IDS. For experiments, the KDD_NSL dataset is used.

Keywords: Intrusion Detection System; Naive Bayes; J48; Random Forest; NSL_KDD dataset.