Apply machine learning techniques to detect malicious network traffic in cloud computing

Abstract Computer networks target several kinds of attacks every hour and day; they evolved to make significant risks. They pass new trends; these open port available on the network. Several tools are designed for this purpose, such as mapping vulnerabilities scanning. Recently, machine learning (ML) is a widespread technique offered feed Intrusion Detection System (IDS) detect malicious network traffic. The core ML models’ detection efficiency relies dataset’s quality train model. This research proposes framework with an model feeding IDS traffic anomalies. uses dataset constructed from normal research’s challenges extracted features used about various distinguish whether it anomaly or regular ISOT-CID part training We added some column features, we approved that feature supports in phase. contains two types first flow, others computed specific interval time. also presented novel increases quality. depending rambling packet payload length flow. Our results experiment produced by encourage other researchers us expand work future work.