Soft computing in computer network security protection system with machine learning based on level protection in the cloud environment

Artificial neural networks (ANN), fuzzy inference systems, approximate reasoning, and derivative-free optimization approaches like evolutionary computation, among others, are all components of Soft Computing (SC), an innovative method for building computationally intelligent methods. Due to its widespread use and benefits, cloud computing is currently a major focus for researchers. The distributed nature of cloud computing and its complete reliance on the internet for service provision present security challenges, the most serious of which is insider Distributed Denial of Service (DDoS) which results in complete deactivation of services. Based on machine learning and the cloud, this study proposes a novel method for improving computing network security. Using a trust-based secure cloud environment and the Kernel principal component encoder architecture, the network monitoring is carried out. The soft computing environment-based detection of a cyberattack on the network is the purpose for the security enhancement. Throughput, QoS, latency, and packet delivery ratio for various monitored cyber security datasets are the focus of the experimental analysis. The proposed technique attained network security analysis of 89%, throughput of 98%, QoS of 66%, latency of 59%, packet delivery ratio of 83%.