A Comparative Analysis of Deep Learning Approaches in Intrusion Detection System

With computers' growth, network-based technology, including advanced communication features, Internet of Things (IoT), automation, and upcoming fifth generation (5G) mobile technology, network security has become challenging to secure applications, systems, and networks. Rapid increase of network devices has created many new attacks and therefore presented significant difficulties for network security to identify threats correctly. Intrusion detection systems (IDSs) guarantee the network's confidentiality, integrity, and availability by monitoring network traffic and blocking any potential intrusions. Despite significant research efforts, IDS still confronts many difficulties in increasing detection efficiency and decreasing false alarm rates. Intrusion detection systems are using machine learning and deep learning-based IDS to identify intrusions throughout the network as quickly as possible. This paper identifies the idea of IDS and the following details the taxonomy developed based on the prominent Machine Learning (ML) and Deep Learning (DL) methods used in NIDS system design. An in-depth analysis of NIDS-based papers is discussed to outline the benefits and weaknesses of the various options. New technology, including ML and DL, and current advances in these NIDS technologies are described with the methodology, assessment metrics, and dataset selections. Through highlighting the existing research difficulties with the longterm scope of the NIDS study to improve machine learning and deep learning-based NIDS. Many novel techniques are using to deal with Intrusion detection systems. However, most are not quick enough to adapt to cyber security defense systems' dynamic and complex nature as the threats surface is growing exponentially with different devices' interfaces. This paper proposes a review of various Intrusion detection system (IDS) capabilities and assets using deep learning techniques. It also suggests a novel idea to automatically adapt the network intrusion detection of the cyber defense architecture to automatically reduce the false alarm rate and optimize the time for detection processes.