Document Type : Research Article



The technological advancement led to increase in the internet usage and created rooms for attackers to exploit our data. Hackers commonly conduct network attacks to alter, damage, or steal private data. Intrusion detection systems (IDS) are the best and most effective techniques when it comes to tackle these threats. An IDS is a software application or hardware device that monitors traffic to search for malicious activity or policy breaches. Intrusion detection is a major challenge for security experts in the cyber world. Traditional IDS failed to detect complex and unknown cyber-attacks. Many IDS models using machine learning (ML) methods have shown good performance in detecting attacks. However, their limitations in terms of data complexity give rise to DL methods. Recent work has shown that deep learning (DL) techniques are highly effective for assisting network intrusion detection systems (NIDS) in identifying malicious attacks on networks. This paper proposed a deep learning model that incorporates learning of spatial and temporal data features by combining the distinct strengths of a Convolutional Neural Network and a Bi-directional LSTM. The publicly available dataset NSL-KDD is used to train and test the model in this paper. The proposed model has a high accuracy rate of 99.22% and detection rate of 99.15%.