Analysis of Efficient Intrusion Detection System using Ensemble Learning

Abstract

Abstract: Our increasingly connected world continues to face an ever-growing amount of network-based attacks. Intrusion detection systems (IDS) are essential security technology for detecting these attacks. Although numerous machine learningbased IDS have been proposed for detecting malicious network traffic, most have difficulty properly detecting and classifying the more uncommon attack types. The research in Cyber Security has raised the need to address the cybercrimes that have caused the requisition of intellectual properties such as the breakdown of computer systems and impairment of important data compromising the confidentiality authenticity and integrity of the user. Considering these scenarios, securing the computer systems and the user using an Intrusion Detection System (IDS) is essential. The performance of IDS was studied by developing an IDS dataset consisting of network traffic features to learn the attack patterns. Intrusion detection is a classification problem wherein various Ensemble Learning (ML) and Data Mining (DM) techniques are applied to classify the network data into normal and attack traffic. Moreover, the types of network attacks changed over the years, so updating the datasets used for evaluating IDS is necessary.