INTELLIGENT NETWORK LOG ANALYSIS AND INTRUSION DETECTION USING MACHINE LEARNING

Abstract

The proliferation of cyberattacks across cloud and enterprise environments has brought to the fore the deficiencies in traditional signature-based security systems. With network logs increasing in a large volume and complexity, it is no longer practical to examine them manually. This paper proposes an intrusion detection system based on machine learning that automatically analyzes logs to identify malicious activities with more efficiency and effectiveness. This research is based on the UNSW-NB15 dataset because it accurately mimics real network traffic and heterogeneous cyberattacks. Data cleaning, encoding, and normalization were done and fed to multiple machine learning models in order to understand how different algorithms react to the same traffic. The Support Vector Machine algorithm yielded the maximum accuracy in distinguishing between normal and malicious traffic. The goal of this research is not only to enhance detection performance but also to simplify security analysis using an open-source, flexible framework that can be adopted by organizations without heavy infrastructure requirements.