Self-Learning Semi-Supervised Machine Learning for Network Intrusion Detection

Abstract

Various machine learning techniques have been used for network intrusion detection. The supervised machine learning methods can achieve high accuracy in classifying the normal and abnormal network data. However, a large amount of labeled data is needed to acquire high accuracy. Labeling large amounts of data could be very costly. Semi-supervised machine learning techniques overcome this problem, since they only use a small amount of labeled data and large amount of unlabeled data. This paper describes our implementation of semi-supervised Support Vector Machine (SVM) and semi-supervised Deep Belief Network (DBN) methods for classifying network data to detect specific attacks. These methods were used to classify the Third International Knowledge Discovery and Data Mining Tools Competition dataset (KDD 1999). The experiments results of both methods are compared and discussed.