Today, with the advancement of technology, cyber attacks are increasing. Personal and corporate computer systems can be exposed to various threats and dangers from hackers and malware, including information theft, forgery, and denial of service, which can cause great material and moral damage to individuals and organizations. Therefore, it is necessary to take security measures in this field. There are many security mechanisms available to prevent security vulnerabilities against various threats. In this research, after a detailed study of network attacks in the cloud computing environment, we identify the criteria for determining applicable attacks in network traffic and explain how to calculate them. The present research introduces an approach based on machine learning to identify network traffic flows, regular and DDoS (DDoS) traffic, identify the victim's attacks, and consider special features. First, pre-processing is done on the data, and then feature selection is made based on the Rank Features method, and after labelling the data, Decision Trees algorithms are used to obtain a model ready for future arrangement. Experimental validation results show that the proposed method can be used to identify cloud computing network traffic. Dense DDoS attacks are more accurately detected, ultimately reducing the misclassification rate and increasing accuracy.
