International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)
Quantum Machine Learning versus Machine Learning for Intrusion Detection in 5G Environments
Ioannis D. Leonidas, Panagiotis I. Radoglou Grammatikis, Evangelos Markakis, Michail‐Alexandros Kourtis, Thomas Lagkas, Georgios Th. Papadopoulos, Vasileios Argyriou, Panagiotis G. Sarigiannidis
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.
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.
Intrusion detection systems (IDS) are essential for identifying cyber threats in complex digital environments. Machine learning (ML) is widely used to improve IDS by detecting anomalies, but classical ML methods often struggle with high-dimensional data and evolving threats. Quantum machine learning (QML) has been proposed as a potential paradigm to overcome some of these limitations, but is constrained by noisy intermediate-scale quantum (NISQ) challenges, affecting quality. This study systematically evaluates three QML models, Pegasos Quantum Support Vector Classifier (QSVC), Variational Quantum Classifier (VQC), and a Hybrid Quantum–Classical Neural Network (HQNN), for network anomaly detection. The models were optimized and tested on the ToN_IoT and NSL-KDD datasets using IBM quantum simulators under both ideal and noisy conditions. Performance was analyzed through the F1-score distribution as a function of circuit complexity, revealing how entanglement and noise affect robustness across different backends. Comparisons with classical models contextualize the current maturity of QML for cybersecurity, while computational time was used as an indicator of model complexity to explore accuracy–efficiency trade-offs. Among all configurations, Pegasos-QSVC achieved the best results, with 94.60% accuracy and an F1-score of 94.13%. The findings provide practical guidelines for designing noise-resilient QML models and highlight their potential for reliable intrusion detection under realistic quantum conditions.
Quantum machine learning (QML) is increasingly investigated for network intrusion detection, but the practical value of current quantum models remains uncertain because many studies rely on small simulated data sets, idealized execution, weak classical baselines, or isolated accuracy comparisons. This study develops and evaluates a resource-aware hybrid quantum-classical intrusion detection framework that combines fixed fidelity quantum kernels, repaired Quantum Kernel Alignment (QKA), a Variational Quantum Classifier (VQC), LightGBM, prototype-based kernel reduction, and probabilistic stacking. Experiments use the UNSW-NB15 benchmark under a leakage-aware preprocessing protocol and repeated evaluation across five random seeds. The experimental program covers 4- and 6-qubit representations, multiple training sizes, prototype budgets, and finite-shot configurations, yielding 260 experimental configurations/runs. The strongest quantum-assisted model, a 6-qubit QKA-VQC-LightGBM stack at 100 samples per class, obtains mean F1=0.8480, MCC=0.7092, ROC-AUC=0.9398, and PR-AUC=0.9302. Repaired QKA improves F1 from 0.8043 for the corresponding fixed kernel to 0.8089, while 50-prototype QKA attains F1=0.8257 with a more favorable kernel-workload trade-off than larger prototype budgets. Finite-shot experiments between 1,024 and 4,096 shots remain stable in simulation. However, full-data LightGBM remains stronger overall (F1=0.8957, MCC=0.8068, ROC-AUC=0.9755, PR-AUC=0.9704), and corrected statistical tests do not establish general quantum superiority. These findings motivate a Selective Quantum Intrusion Detection System (S-QIDS), in which classical inference handles high-confidence traffic and quantum processing is reserved for uncertain, novel, or high-risk observations. The study therefore reframes near-term quantum intrusion detection from unconditional quantum advantage toward measurable quantum utility, quantum-classical complementarity, and resource-aware quantum intervention.
Intrusion Detection Systems (IDSs) are a cornerstone of modern cybersecurity; however, their performance is increasingly constrained by high-dimensional network traffic and the scalability limitations of classical machine learning approaches. Quantum Machine Learning (QML) has recently emerged as a promising paradigm by leveraging quantum feature spaces and hybrid quantum–classical optimization. In this work, we present a unified and reproducible benchmarking framework for QML-based intrusion detection under realistic Noisy Intermediate-Scale Quantum (NISQ) constraints. The proposed framework integrates hybrid Quantum Neural Networks (QNNs) and Quantum Support Vector Machines (QSVMs) within a consistent experimental pipeline, enabling a systematic comparison of quantum models, embedding strategies, and dimensionality reduction techniques. Experiments are conducted on the NSL-KDD benchmark dataset for both binary (normal versus attack) and multiclass intrusion detection tasks. Multiple quantum embedding strategies, including angle, amplitude, and Instantaneous Quantum Polynomial (IQP) embeddings, are evaluated in conjunction with PCA-based dimensionality reduction to analyze trade-offs between expressivity, circuit complexity, and computational cost. The proposed models are benchmarked against strong classical baselines under identical preprocessing and evaluation conditions. The results demonstrate that QNN- and QSVM-based IDS models achieve competitive and, in several scenarios, superior performance compared to classical approaches, particularly in multiclass settings characterized by nonlinear and imbalanced data distributions. In addition, we provide an in-depth analysis of scalability limitations, training complexity, and NISQ feasibility, highlighting practical considerations for real-world deployment. To ensure full reproducibility, all implementation details, datasets, and experimental configurations are publicly available at: https://github.com/raidanis/QML-IDS-NSLKDD. These findings position hybrid QML as a promising complementary paradigm for next-generation intrusion detection systems, particularly in low-dimensional and high-complexity feature spaces.
Intrusion Detection Systems (IDS) play a fundamental role in safeguarding digital infrastructures against cyber threats. Quantum Machine Learning (QML) presents a promising frontier in this domain, offering potential computational speedups and improved management of complex datasets. However, its practical deployment is currently limited by the constraints of Noisy Intermediate-Scale Quantum (NISQ) devices. This work explores the application of various QML approaches, specifically Quantum Support Vector Classifiers (QSVC), Variational Quantum Classifiers (VQC), and hybrid quantum-classical neural networks for anomaly detection tasks. The models were fine-tuned and benchmarked using the ToN_IoT dataset, with performance assessed on IBM's noisy quantum simulators to evaluate their behavior under realistic noise conditions. Results indicate that the Pegasos-QSVC model outperformed others, reaching an accuracy of 93.05% and an F1 score of 93.73%. Through a comparative analysis of different circuit architectures, this study identifies strategies to improve the robustness of QML systems, emphasizing their emerging potential in cybersecurity scenarios.
Intrusion detection in unmanned-aerial-vehicle (UAV) swarms is complicated by high mobility, non-stationary traffic, and severe class imbalance. Leveraging a 120 k-flow simulation corpus that covers five attack types, we benchmark three quantum-machine-learning (QML) approaches - quantum kernels, variational quantum neural networks (QNNs), and hybrid quantum-trained neural networks (QT-NNs) - against strong classical baselines. All models consume an 8-feature flow representation and are evaluated under identical preprocessing, balancing, and noise-model assumptions. We analyse the influence of encoding strategy, circuit depth, qubit count, and shot noise, reporting accuracy, macro-F1, ROC-AUC, Matthews correlation, and quantum-resource footprints. Results reveal clear trade-offs: quantum kernels and QT-NNs excel in low-data, nonlinear regimes, while deeper QNNs suffer from trainability issues, and CNNs dominate when abundant data offset their larger parameter count. The complete codebase and dataset partitions are publicly released to enable reproducible QML research in network security.
Quantum machine learning (QML) algorithms for intrusion detection systems in software-defined networks are investigated, and their effectiveness is compared with their classical machine learning methods. The University of Nevada - Reno intrusion detection dataset (UNR-IDD) is used to evaluate different QML models, including quantum k-nearest neighbors (QKNNs), quantum support vector machines (QSVMs), quantum neural networks (QNNs), and hybrid quantum neural networks (HQNNs). These models were tested with quantum simulators to evaluate their potential advantages in processing complex datasets. The results show that HQNN and QSVM have higher accuracy than their classical SVM and NN counterparts. This study shows the potential of leveraging QML to enhance precision. References to other works that dive into efficiency and complexity are included.