1. Introduction
Many firms rely heavily on online computing systems to run businesses and thus become targets for cyber-attacks, so they prioritize artificial intelligence-based intrusion detection systems (IDSs) among their network security procedures [1,2,3]. According to Markevych and Dawson [4], the high complexity of modern cyber-attacks requires more innovations when proposing and applying robust IDSs to protect critical assets and network data by identifying and classifying network traffic and detecting anomalous behavior. With the rapid increase in the amount of available online data, the possibility of being hacked by different intrusion attacks also increases [5]. The application of deep learning and machine learning architectures in IDSs showed interesting results in the accuracy and efficiency of detecting diverse cyber threats in network environments by learning from…
