The present review paper delves into the subject of cloud attack classification through the utilisation of deep learning neural networks and supervised machine learning. The article delineates various methodologies that have been employed in this domain, encompassing decision tree algorithms, convolutional neural networks, and deep learning-based intrusion detection systems. The results of these methodologies have exhibited promise, as numerous studies have reported elevated precision levels in the identification and categorization of security threats pertaining to cloud computing. Furthermore, the manuscript examines the obstacles and constraints of said methodologies, including the requirement for substantial quantities of annotated data and the possibility of erroneous outcomes. This review paper offers an analysis of the present state of cloud attack classification and the potential of deep learning and supervised machine learning techniques in augmenting cloud security

.