QML-IDS: Quantum Machine Learning Intrusion Detection System

TL;DR

QML-IDS is a novel intrusion detection system leveraging quantum machine learning to improve attack detection accuracy, outperforming classical methods, and demonstrating the potential of quantum-enhanced cybersecurity.

Contribution

This paper introduces QML-IDS, the first IDS combining quantum and classical techniques for improved network attack detection.

Findings

QML-IDS outperforms classical ML in attack detection accuracy.

QML-IDS is effective in binary and multiclass classification tasks.

Experimental results validate the potential of quantum-enhanced cybersecurity solutions.

Abstract

The emergence of quantum computing and related technologies presents opportunities for enhancing network security. The transition towards quantum computational power paves the way for creating strategies to mitigate the constantly advancing threats to network integrity. In response to this technological advancement, our research presents QML-IDS, a novel Intrusion Detection System~(IDS) that combines quantum and classical computing techniques. QML-IDS employs Quantum Machine Learning~(QML) methodologies to analyze network patterns and detect attack activities. Through extensive experimental tests on publicly available datasets, we show that QML-IDS is effective at attack detection and performs well in binary and multiclass classification tasks. Our findings reveal that QML-IDS outperforms classical Machine Learning methods, demonstrating the promise of quantum-enhanced cybersecurity solutions for the age of quantum utility.