Cloud Computing Malware Detection Using Feature Selection Based on Optimized White Shark Algorithm (WSO)

The majority of information technology organizations nowadays prefer cloud computing as their main choice due to improvements in information technology. However, as a result of cloud computing's vast and open architecture, which makes it vulnerable to hacker attacks, the security of data remains an important concern. As a consequence, ensuring the security and integrity of data has become crucial while constructing an abnormal intrusion detection system utilizing machine learning algorithms represents a method to potentially detect intrusions. Recurring clouding as well as prevention. Using machine learning algorithms and revised intrusion datasets is necessary to overcome the challenge of finding effective and optimal network intrusion detection systems. The White Shark Optimization approach works along with Support Vector Machines (SVM). The suggested algorithm's effectiveness is assessed using metrics including accuracy and recall. When results of previous research employing both of the two datasets (NSL-KDD and Kyoto) for predicting the detection of abnormal infiltration are compared to the proposed algorithm based on SVM, it is determined that the white shark optimization algorithm produced the best accuracy, at 99.8%.