Abstract
An intrusion detection system (IDS) is a software application or hardware appliance that monitors traffic on networks and systems to search for suspicious activity and known threats, sending up alerts when it finds such items. In these recent years, attention has been focused on artificial neural networks (ANN) techniques, especially Deep Learning approach on anomaly-based detection techniques; because of the huge and unbalanced datasets, IDS encounters real data processing problems. Thus, different techniques have been presented which can handle this problem. In this paper, a deep learning model or technique based on the Convolutional Neural Network (CNN) is proposed to improve the accuracy and precisely detect intrusions. The entire proposed model is divided into four stages: data collection, data pre-processing, the training and testing stage, and performance evaluation.