Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection

TL;DR

This paper proposes a Bayesian Optimization-based framework to tune machine learning algorithms like SVM, Random Forest, and k-NN for anomaly detection in network security, demonstrating improved accuracy and reduced false alarms.

Contribution

It introduces a novel framework that applies Bayesian Optimization to optimize parameters of multiple machine learning algorithms for network anomaly detection.

Findings

Enhanced detection accuracy and precision.

Lower false alarm rates.

Effective parameter tuning demonstrated on ISCX 2012 dataset.

Abstract

Network attacks have been very prevalent as their rate is growing tremendously. Both organization and individuals are now concerned about their confidentiality, integrity and availability of their critical information which are often impacted by network attacks. To that end, several previous machine learning-based intrusion detection methods have been developed to secure network infrastructure from such attacks. In this paper, an effective anomaly detection framework is proposed utilizing Bayesian Optimization technique to tune the parameters of Support Vector Machine with Gaussian Kernel (SVM-RBF), Random Forest (RF), and k-Nearest Neighbor (k-NN) algorithms. The performance of the considered algorithms is evaluated using the ISCX 2012 dataset. Experimental results show the effectiveness of the proposed framework in term of accuracy rate, precision, low-false alarm rate, and recall.