An Efficient Supervised Model for Intrusion Detection
An Intrusion Detection System (IDS) is a device or software application that monitors a network or systems for
malicious activity. In this paper, we consider deep learning is a new approach in this field. The main contributions of this
paper are as follows. Firstly, we proposed a supervised model, GRU+BN+Dropout, to detect intrusion. The architecture of
this model includes three main layers such as GRU hidden layer, Batch Normalization (BN) layer, and Dropout layer.
Secondly, we constructed a learning algorithm of the proposed model. Finally, we have implemented our model and then
evaluated its performance classification using several of methods such as confusion matrix, F-measure, and ROC curve. Our
model achieved 97% of ROC curve and 94% of F-measure.
Keywords- Deep learning, Gate Recurrent Unit, Intrusion Detection System, Batch Normalization, Dropout, KDD Cup’ 99.