Decision Tree Based Network Intrusion Detection for Cyber Security Application

One of the most significant challenges facing cyber security professionals in the modern day is intrusion detection. There have been a substantial number of methods produced that are based on machine learning techniques that have been developed. So, to detect the breach, the machine learning techniques that we developed were used. When we use the method, not only are we able to detect an intrusion, but we can also identify the specifics of the attacker. IDS may be broken down into two primary categories: network-based and host-based. Installed at network points like routers and gateways, a Network-based Intrusion Detection System or NIDS, monitors network traffic and searches for indications of intrusions. In this study, the classification decision tree method known as C4.5 is presented. When it comes to data mining, the C4.5 method is utilized as a Decision Tree Classifier. This means that it may be put to use to produce a judgment that is predicated on a particular data sample. The findings of the simulation indicate that the strategy being presented yields significantly excellent outcomes in terms of recall, precision, F1-Score, accuracy and Error Rate. The total accuracy that was reached is 96.3%, which is equivalent to around 97% when accounting for the error rate of 3%.