Quantum Machine Learning versus Machine Learning for Intrusion Detection in 5G Environments
Year: 2026
Type: conference-paper
Abstract: Quantum machine learning (QML) is often motivated by the promise of richer feature representations and similarity measures, but its practical value for realistic, multiclass telecom-security data remains unclear under near-term constraints. This paper presents a unified benchmark of classical, quantum-inspired, and trainable QML approaches for multiclass intrusion detection on Packet Forwarding Control Protocol (PFCP) control-plane traffic in 5G Core networks. We evaluate classical baselines, including a Radial Basis Function Support Vector Machine (RBF-SVM) and Extreme Gradient Boosting (XGBoost), a quantum-inspired k-nearest neighbors classifier based on an analytic SWAP-test kernel, parametrized quantum classifiers with hardware-efficient and data-reuploading ansatzes, and trainable quantum kernels optimized via the quantum kernel alignment method. Across multiple aggregation windows of the PFCP APP Layer dataset, the quantum-inspired kernel method is the most consistently competitive approach. In particular, on the 240 s window, qkNN achieves 62.1% accuracy and 61.6% macro F1, outperforming XGBoost, which reaches 59.9% accuracy and 60.3% macro F1, and RBF-SVM, which reaches 55.1% accuracy and 51.7% macro F1. Fully trainable quantum models yield more modest performance and exhibit higher sensitivity to scaling and optimization. Overall, the results indicate that quantum-inspired kernel methods currently provide the most practical benefits for PFCP intrusion detection at realistic dataset sizes, whereas trainable quantum machine learning models require more robust optimization and improved resource scaling to deliver reliable improvements.
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7204445648