A Survey on Machine Learning based Intrusion Detection System on NSL-KDD Dataset

Abstract

Nowadays, Intrusion detection system is the most emerging trend in our society. Intrusion detection system act as a defensive tool to detect the security attacks on the web. It is a device or software application that monitor network for malicious activity and alert to the administrator. Intrusion Detection System work by either looking for signatures of known attacks or deviations of normal activity. In this paper we have survey various type of intrusion detection system and techniques which are based on Support Vector Machine (SVM), machine learning, fuzzy logic, supervised learning. Also we have compared various techniques on the basis of their accuracy on NSL-KDD Datasets. We have also suggested that if we use hybrid combination of SVM and Machine learning then the accuracy can be improved.