ML technique integrated system development for protecting against attacks through CC

Recent technological breakthroughs have encouraged users to adopt a cloud-based infrastructure. The distributed nature of cloud systems poses a significant challenge in terms of security. Due to its high vulnerability to intruders and potential attacks, ensuring safety and confidentiality are substantial obstacles to the success of the on-demand service. An exponential surge in network traffic has created a fertile environment for the emergence of increasingly complex and widespread security threats. Many Intrusion Detection Systems (IDS) have been proposed to work with Cloud Computing (CC). IDS overfits need to be more accurate at categorizing and precise when given a large and varied network data set. This study shows the best and fastest way to find problems in a CC setting. In this case, a mixed Machine-Learning (ML) approach is utilized. Enhanced Heap Optimization (EHO) is an approach employed during the planning stage to ensure the quality of the data by getting rid of data that is not needed. The research picks the best characteristics with the help of the Chaotic Red Deer Optimization Algorithm (CRDOA). A Dynamic Kronecker Neural Network (D-KNN) has been shown to protect against cloud hacks, find risks, and sort information.