Survey of Machine Learning HIDS Techniques

The development of cyber-attacks has unprecedented effect on businesses and governments. The recent years have witnessed various number of security breaches against organizations equipped by diverse cybersecurity solutions. These attacks showed the limitations of the current security systems to remediate the advanced threats. This critical challenge poses a vital need to find new techniques to detect the recently developed malwares called Zero-Day Threats. This type of attacks cannot be discovered by signature-based scanning and traditional cybersecurity systems. In addition, they can bypass the network security appliances by concealing malwares in the encrypted channels such as Virtual Private Network (VPN) and Hypertext Transfer Protocol Secure (HTTPS). Therefore, there is a great importance to study the endeavors of developing a Host-based Intrusion Detection System (HIDS) using Artificial Intelligence (AI) techniques to protect computers against sophisticated cyber-attacks. This paper will discuss and compare the recent proposed techniques using Machine Learning at the host level to detect the advanced cybersecurity attacks based on the behavioral impact of these attacks on computers.