With the great advent of Cloud technology, protecting the data over the cloud environment is essential. Cloud computing is often confronted with several threats such as the insecure interface, abuse of cloud computing, data loss, anonymous database hacking, crashing, and malicious insiders. Due to the enormous amount of increased security threats on various organizations, the security-enhanced cloud system has greatly impacted many real-time systems. Moreover, in the entire cloud data determining the attack types is a crucial and time-consuming task.
Several machine learning and deep learning models have introduced different security solutions to cloud environments, such as static verification of user behavior in the cloud analyzing the security status of the monitored cloud system by applying machine learning and complex event processing rules. Though, adopted supervised learning models fail to detect the unknown or new anomalies due to the behavior variations among the attacks. Thus, enhanced transfer learning provides potential benefits to the cloud environment based on the anomaly-aware cloud security mechanisms that substantially preserve the cloud environment from emerging anomalies. Also, it enforces time-efficient threat detection of new attacks and classification of existing attacks models in the massive cloud environment.