Unsupervised Feature Learning using a Novel Non-Symmetric Deep Auto Encoder (NDAE) Model for NIDS Framework

Abstract

 Network intrusion identification frameworks play a pivotal role in guarding computer networks. As of late, one of the fundamental concentrations within Network Intrusion Detection System(NIDS) inquire about the usage and application of Machine Learning(ML) Techniques. This paper proposed to enable NIDS network traffic for novel deep learning model. This paper introduces the novel approach which proposes Non Symmetric Deep Auto Encoder(NDAE) for unsupervised feature learning. As well, it intended novel deep learning classification display to utilizing stacked NDAEs. The Proposed classifier has been performed in KDD Cup ‘99 and NSL KDD data set.. The KDD Cup 99 and NSL-KDD data set particularly are performance evaluated network intrusion detection data sets. Our contribution work is to implement intrusion prevention system(IPS) having functionality but more sophisticated systems which are capable of taking instant actions in order to stop or reduce malicious behaviour.