A Systematic Analysis of Machine Learning Algorithms for Cloud DDoS Attack Detection

Computing in the cloud is a relatively recent innovation that involves sending data processing jobs to third-party service providers through the Internet. Cloud computing comes with several benefits, such as reduced overhead costs, expandable capabilities, and changeable pricing. However, there are several concerns about the cloud's level of security. DDoS assaults, also known as distributed denial-of-service attacks, pose a danger to cloud infrastructure. In order to defend against DDoS assaults in the cloud, a variety of different machine learning algorithms have been developed. However, there is not yet a general agreement on employing machine learning to protect against DDoS assaults in the cloud. In addition, as the number of relevant literature increases, it becomes more challenging to monitor all of it, much alone characterize the current state of the art or identify emerging gaps in study. This project aims to conduct a literature review on DDoS machine learning approaches for the cloud. To that aim, the purpose of this study is to undertake a methodical examination of the existing research that discusses cloud machine learning algorithms for DDoS in an attempt to synthesize the evidence associated with this topic.