International Conference on Advanced Communication Technologies and Networking (CommNet)
Hybrid Quantum–Classical Machine Learning for Cyber Threat Detection: A Comparative Assessment of Quantum Kernel and Variational Quantum Circuit Techniques
Mohammed Khaldoune, Samia El Haddouti, Habiba Chaoui
The growing complexity of cyber threats has revealed the limitations of classical machine learning techniques, motivating the exploration of Quantum Machine Learning in threat detection systems for enhancing detection accuracy and computational efficiency. This study presents a comparative evaluation of two prominent quantum machine learning approaches: quantum kernel methods and variational quantum circuits, applied across diverse threat detection tasks. Our analysis, supported by recent empirical findings, demonstrates that hybrid quantum-classical architectures can reach or surpass classical baselines while requiring few qubits, shallow circuits, and reduced parameter count. Despite these promising results, several challenges remain, including data loading and state preparation overheads, trainability constraints, and limited empirical validation. In response, we propose theoretical guidance and practical criteria to facilitate reproducible and effective application of Quantum Machine Learning in cyber threat detection, bridging the gap between emerging theory and empirical practice.
The growing complexity of cyber threats has revealed the limitations of classical machine learning techniques, motivating the exploration of Quantum Machine Learning in threat detection systems for enhancing detection accuracy and computational efficiency. This study presents a comparative evaluation of two prominent quantum machine learning approaches: quantum kernel methods and variational quantum circuits, applied across diverse threat detection tasks. Our analysis, supported by recent empirical findings, demonstrates that hybrid quantum-classical architectures can reach or surpass classical baselines while requiring few qubits, shallow circuits, and reduced parameter count. Despite these promising results, several challenges remain, including data loading and state preparation overheads, trainability constraints, and limited empirical validation. In response, we propose theoretical guidance and practical criteria to facilitate reproducible and effective application of Quantum Machine Learning in cyber threat detection, bridging the gap between emerging theory and empirical practice.
The growing complexity and velocity of cyber threats in high-security environments such as defense, critical infrastructure, and intelligence networks necessitates a paradigm shift in threat detection capabilities. Traditional cybersecurity systems, including those enhanced by classical machine learning algorithms, often struggle to process and classify massive volumes of heterogeneous and encrypted data in real time. This shortcoming is particularly evident in the context of advanced persistent threats (APTs), polymorphic malware, and insider attacks, which require rapid adaptation and heightened sensitivity to anomalous behavior.Quantum Machine Learning (QML), an emerging interdisciplinary field at the intersection of quantum computing and artificial intelligence, presents a promising avenue for augmenting threat detection mechanisms. Leveraging quantum phenomena such as superposition and entanglement, QML models offer potential advantages in processing speed, pattern recognition, and feature space transformation that can outperform their classical counterparts in high-dimensional data analysis. This paper explores the application of QML to threat detection in high-security networks, proposing a hybrid quantum-classical framework that integrates quantum-enhanced classifiers such as quantum support vector machines and variational quantum circuits into existing detection pipelines.The study outlines a technical overview of quantum computing principles relevant to cybersecurity, critically evaluates existing detection architectures, and presents simulation-based case studies to assess performance metrics, including detection accuracy and false positive rates. It further examines the limitations of current quantum hardware, algorithmic constraints, and emerging ethical and operational considerations. The findings suggest that while QML is still constrained by hardware maturity and integration complexity, it holds transformative potential for proactive, intelligent, and adaptive cyber defense systems in high-stakes environments. This research contributes to ongoing efforts to future-proof cybersecurity infrastructure against both classical and post-quantum threat landscapes.
Quantum machine learning (QML) has recently emerged as a promising research direction at the intersection of artificial intelligence, quantum computing, and cybersecurity. Among its potential applications, intrusion detection remains particularly relevant due to the growing complexity of cyber threats and the increasing need for adaptive and efficient detection mechanisms. This paper explores the applicability of lightweight quantum and hybrid quantum-classical machine learning approaches for intrusion detection in resource-constrained experimental settings. The study is designed as a comparative analysis of selected models, including variational and kernel-based quantum techniques, alongside a conventional classical baseline, in order to evaluate their practical potential for cybersecurity tasks.The experimental framework relies on a reduced and preprocessed cybersecurity dataset and is implemented in a simulated quantum environment using accessible open-source tools. The comparison considers standard performance indicators such as classification effectiveness and computational efficiency, while also reflecting on broader dimensions of model suitability for security-oriented applications. In addition to the technical evaluation, the paper addresses several ethical considerations associated with the use of QML in cybersecurity, including limited transparency, risks related to biased or imbalanced training data, and the operational implications of incorrect classifications in intrusion detection scenarios.Rather than claiming immediate quantum advantage, the study aims to provide a realistic and methodologically grounded perspective on the current role of QML in cybersecurity research. The expected contribution is twofold - first, to outline a feasible experimental approach for evaluating QML methods in intrusion detection and second, to highlight the importance of combining performance-oriented assessment with ethical and interpretability-related considerations when examining emerging intelligent security solutions.
Emerging cyber threats demand novel detection and analysis paradigms that classical machine learning approaches are increasingly unable to address at requisite scale and speed. Quantum Machine Learning (QML), leveraging quantum mechanical phenomena such as superposition and entanglement, has emerged as a promising framework for cyber threat intelligence (CTI). This scoping review systematically examines 24 published works from 2020 to 2025 following the PRISMA-ScR protocol. We classify QML frameworks like Quantum Support Vector Machines (QSVM), Quantum Neural Networks (QNN), Variational Quantum Circuits (VQC), and Quantum Convolutional Neural Networks (QCNN) across four primary CTI domains: intrusion detection, malware classification, anomaly detection, and phishing detection. Results show that QML models achieved up to 98% accuracy in intrusion detection and 97% in IoT anomaly detection on curated benchmark datasets. Critical caveats apply: 83.3% of studies relied exclusively on quantum simulators rather than real hardware, most benchmarks used datasets predating 2017, and the classical pre-processing and post-processing overheads in hybrid architectures substantially qualify reported speedup claims. We assess hardware constraints in Noisy Intermediate-Scale Quantum (NISQ) devices, data encoding bottlenecks, and missing quality benchmarks. NIST post-quantum cryptography standards (FIPS 203-205, August 2024) and IBM quantum hardware milestones are discussed as contextual anchors. A structured research agenda concludes the review.
Under tight feature and compute budgets, classical threat detection pipelines often degrade on near-decision-boundary events. Small quantum processors are now available, but existing work inadequately shows whether quantum components improve end-to-end threat detection under the above resource constrained conditions. This paper tries to address this gap with a hybrid architecture that uses a compact multilayer perceptron layer to compress the information in data and then routes the processed features to a few qubit quantum heads implemented in quantum support vector machine (QSVM) and variational quantum circuit (VQC) models. On a simulation platform, we benchmark these hybrid models against classical models with comparable parameter budgets on two representative cybersecurity tasks, network intrusion detection on NSL-KDD dataset and spam filtering on Ling-Spam dataset. To validate their precision on real quantum hardware, we deploy the best 4-qubit QSVM model on an IBM Quantum device with noise-aware execution, evaluated on a smaller sub-dataset. In the results, shallow quantum heads consistently match, and on difficult near-boundary cases modestly reduce missed attacks and false alarms compared to classical models using the same features. Hardware validation results track the simulation behavior closely enough that the remaining gap is dominated by device noise rather than model design. Furthermore, we conduct adversarial attacks to test the robustness of one QSVM model. Taken together, the study shows that even on small, noisy devices, carefully engineered quantum components may function as competitive, budget-aware components in practical cyber threat detection applications.
With the potential for quantum computing to completely transform cybersecurity, quantum machine learning is becoming a ground-breaking technology. Cyber-attacks have been successfully countered by traditional network defense systems, which mostly use conventional machine learning (ML) techniques. However, the growing complexity of assaults and the exponential expansion of network data reveal the shortcomings of traditional methods, especially with regard to speed and scalability. By utilizing quantum algorithms like Quantum Support Vector Machines (QSVM), Quantum Neural Networks (QNN), and Variational Quantum Circuits (VQC), Quantum Machine Learning (QML) presents a viable substitute. These methods are especially well-suited for real-time network defense scenarios since they show the capacity to handle high-dimensional data, identify complex patterns, and increase computational efficiency. In this research, the effectiveness of QML techniques in network defense is thoroughly examined and contrasted with that of traditional machine learning techniques. The study emphasizes how QML may surpass conventional models in terms of accuracy, scalability, and resilience against sophisticated threats by concentrating on use cases like intrusion detection, malware analysis, and anomaly detection. The necessity for hybrid quantum-classical models and the present constraints of quantum hardware are among the difficulties that are discussed in the study. This study highlights the revolutionary potential of QML in strengthening network defense mechanisms and identifies crucial areas for further research, paving the road for a secure digital future by combining theoretical ideas with experimental discoveries.
Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.