An effective semi-supervised model for intrusion detection using feature selection based LapSVM
Xiaofeng Zhang, Peidong Zhu, Jianwei Tian, Jiexin Zhang · 2017
Intrusion detection techniques have been extensively used as a protective measure against network attacks. Machine learning (ML) has been widely recognized as an effective method for data based intrusion detection analysis. Especially, semi-supervised ML approaches apply both labelled and unlabelled data to train the detection model, which can avoid the high cost of labelling data. In this paper, we propose an effective semi-supervised ML framework for intrusion detection. Specifically, the framework adopts Laplacian Support Vector Machine (LapSVM) as its training model and uses information gain based feature selection method to improve the performance. The experiment results on NSL-KDD demonstrate that our framework is capable of achieving a high accuracy value of 97.8%, while the false-positive rate is 2%.