Anomaly-Based Intrusion Detection by Machine Learning: A Case Study on Probing Attacks to an Institutional Network

TL;DR

This paper explores the use of anomaly-based machine learning models, including ensemble and CNN, to detect probing network attacks, demonstrating high accuracy on real and benchmark datasets.

Contribution

It introduces and evaluates CNN and ensemble models for intrusion detection in institutional networks, showing improved accuracy over traditional methods.

Findings

CNN model achieved slightly higher accuracy than ensemble.

Models performed reliably on real and benchmark datasets.

High detection accuracy for probing attacks.

Abstract

Cyber attacks constitute a significant threat to organizations with implications ranging from economic, reputational, and legal consequences. As cybercriminals' techniques get sophisticated, information security professionals face a more significant challenge to protecting information systems. In today's interconnected realm of computer systems, each attack vector has a network dimension. The present study investigates network intrusion attempts with anomaly-based machine learning models to provide better protection than the conventional misuse-based models. Two models, namely an ensemble learning model and a convolutional neural network model, were built and implemented on a data set gathered from a real-life, institutional production environment. To demonstrate the models' reliability and validity, they were applied to the UNSW-NB15 benchmarking data set. The type of attack was limited to probing attacks to keep the scope of the study manageable. The findings revealed high accuracy rates, the CNN model being slightly more accurate.