Network Intrusion Detection System using Supervised Learning based Voting Classifier

Abstract

As the internet has advanced nowadays, so has the frequent of internet-based attacks. Intrusion Detection (ID) is among the most widely used methods for identifying hostile activity in a network by examining its traffic. Machine-learning [ML] approaches are increasingly being used to solve all those situations where rationally comprehending the process of interest is difficult. A hugeamount of strategies on the basis of ML methodologies are being developed. In networked systems, intrusion detection is an issue in which, while it is not essential to interpret the measures obtained from a process, it is critical to acquire a response from a classification algorithm whether the network traffic is influenced by anomalies. To enhance network security, a strong Intrusion Detection System (IDS) is essential. In this paper, various ML algorithms have been implemented and compared for predicting whether there is intrusion in network data traffic or not.