Cyber-security trust model through adaptive cloud authentication protocol for web application

The development and growth of internet-based technologies brings challenges in cyber-security from cyberattack organizations. It is necessary to develop an appropriate cyber-security scheme through a structured machine learning algorithm implemented in the cloud architecture. The aim of our research is to design a cloud-based architecture using an adaptive cloud authentication protocol to develop the trust model for cyber-security systems. Here, the structure learning of Bayesian networks (SL_BN) is developed with an ensemble architecture of machine learning that is integrated with the support vector machine and adaptive fuzzy-based genetic algorithm (SVM_AFGA). The fuzzy logic sets rules for using web applications at the authorized web address. The experimental results show that parametric analysis based on the cyber-security authentication model is based on median delay, transmission level overhead, and security of the network. Moreover, the parameters based on the SL-BN ensemble architecture are average runtime, accuracy, and network efficiency. (c) 2023 SPIE and IS&T