A Network Intrusion Detection Approach Using Variant of Convolution Neural Network

Intrusion detection system(IDS) is a preventing measure against different harmful cyber-attacks. It has a key role in securing our information and communication technology system. As the internet evolved, the dynamic growth of network traffic data generated which become a challenge for traditional machine learning algorithms. Performance of a classifier solely depends on feature selection and classifier. Traditional machine learning algorithms can't perform well with huge network traffic dataset. So ML algorithms are not optimistic. In this paper, we implemented Convolution neural network(CNN-1D) for NIDS(Network Intrusion detection system) on NSL-KDD benchmark dataset. CNN automatically fetch network traffic features from the dataset. in this paper, we trained our model 500 epoch. We also compared performance of different ML(machine learning) algorithms & DL(deep learning) approaches with our CNN-1D approach with metrics of AC (accuracy), DR (detection rate) and FAR (False alarm rate).