Machine Learning Methods for Intrusion Detection in Computer Networks: A Comparative Analysis

OpenAlex English

The widespread use of the Internet and the exponential increase in the number of devices connected to it bring along significant challenges as well as numerous benefits. The most important of these challenges, and the one that needs to be addressed as soon as possible, is cyber threats. These attacks against individuals, organisations and even entire nations can lead to financial, reputational and temporal losses. The aim of this research is to compare and analyse machine learning methods to create an anomaly-based intrusion detection system that can detect and identify network attacks with a high degree of accuracy. Examining, tracking and analysing the data patterns and volume in a network will enable the creation of a reliable Intrusion Detection System (IDS) that will maintain the health of the network and ensure that it is a safe place to share information. To have high accuracy in the prediction of the data set by using Decision Trees, Random Forest, Extra Trees and Extreme Gradient Boosting machine learning techniques. CSE-CIC-IDS2018 dataset containing common malicious attacks such as DOS, DDOS, Botnet and BruteForce is used. The result of the experimental study shows that the Extreme Gradient Boosting algorithm has an impressive success rate of 98.18% accuracy in accurately identifying threatening incoming packets.