Abstract

The intrusion detection system (IDS) is required to identify network attacks, and combating them is one of the most important defence mechanisms against threats and attacks against cloud computing. It is used in several areas, such as information security and machine learning, including deep learning, to create effective intrusion detection systems. Threats can be recognised by such systems with ease and accuracy. However, harmful threats always arise, so networks need intelligent security solutions. Therefore, one of the most vigilant research topics is developing effective intrusion detection systems. Currently, many fields, particularly information security, machine learning, and deep learning, are creating effective intrusion detection systems. Such systems can accurately detect known threats; however, as new and evolving threats continue to emerge, networks must apply a higher level of protection. Therefore, this paper proposes a hybrid intrusion detection system with automated threat response, enhancing IDS performance through feature reduction, dataset balancing, and hybrid model methodologies.