An Enhanced Machine Learning Security Algorithm for the Anonymous user Detection in Ultra Dense 5G Cloud Networks

Abstract

In general, high-density network services have a large number of users. This is seen as the main problem of that network. As users increase, so does the amount of service provided to them. Thus, have to pay separate attention to serving and serving them. It is imperative to ensure their maximum security if they are the primary user. Thus, security management is much less on high density 5G networks. A security algorithm has been proposed to improve these issues. This algorithm, designed for machine learning, first detects the primary user. Their security is prioritized by calculating their input and output times. It is also designed to detect secondary users and anonymous user. These anonymous users were creating the resource utilization and security vulnerabilities in the network. So, the primary user protection and anonymous user identification getting more priority in the ultra dense cloud networks.