Paper Title
An Efficient Supervised Model for Intrusion Detection
Abstract
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.
Author - Thi-Thu-Huong Le, Howon Kim
Published : Volume-4,Issue-4 ( Apr, 2017 )
DOIONLINE Number - IJAECS-IRAJ-DOIONLINE-7651
View Here
|
|
| |
|
PDF |
| |
Viewed - 54 |
| |
Published on 2017-06-19 |
|
|
|
|
|
|