In recent years, we have seen an increase in computer attacks through our communication networks worldwide, whether due to cybersecurity systems’ vulnerability or their absence. This paper presents three quantum models to detect distributed denial of service attacks. We compare Quantum Support Vector Machines, hybrid QuantumClassical Neural Networks, and a two-circuit ensemble model running parallel on two quantum processing units. Our work demonstrates quantum models’ effectiveness in supporting current and future cybersecurity systems by obtaining performances close to 100%, being 96% the worst-case scenario. It compares our models’ performance in terms of accuracy and consumption of computational resources.
In recent years, we have seen an increase in computer attacks through our communication networks worldwide, whether due to cybersecurity systems’ vulnerability or their absence. This paper presents three quantum models to detect distributed denial of service attacks. We compare Quantum Support Vector Machines, hybrid QuantumClassical Neural Networks, and a two-circuit ensemble model running parallel on two quantum processing units. Our work demonstrates quantum models’ effectiveness in supporting current and future cybersecurity systems by obtaining performances close to 100%, being 96% the worst-case scenario. It compares our models’ performance in terms of accuracy and consumption of computational resources.
This chapter provides a comprehensive overview of the recent developments in quantum machine learning for intrusion detection systems. The authors review the state of the art based on the published work “Quantum Machine Learning for Intrusion Detection of Distributed Denial of Service Attacks: A Comparative View” and its relevant citations. The chapter discusses three quantum models, including quantum support vector machines, hybrid quantum-classical neural networks, and a two-circuit ensemble model, which run parallel on two quantum processing units. The authors compare the performance of these models in terms of accuracy and computational resource consumption. Their work demonstrates the effectiveness of quantum models in supporting current and future cybersecurity systems, achieving close to 100% accuracy, with 96% being the worst-case scenario. The chapter concludes with future research directions for this promising field.
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.
The application and assessment of quantum-based anomaly detection models in cybersecurity are examined in this work. The efficacy of quantum machine learning approaches for detecting several cyber threats, including Denial of Service (DoS), Remote-to-Local (R2L), and botnet penetration, using two well-known intrusion detection datasets: NSL-KDD and CICIDS2017. Angle and amplitude encoding techniques are worn to preprocess and instruct traditional data into quantum-readable formats, making it compatible with quantum circuits. Due to the present constraints of Noisy Intermediate-Scale Quantum (NISQ) devices, the models are developed using Qiskit, using parameterized quantum layers via the TwoLocal ansatz, and simulated on classical hardware using Qiskit Aer. Metrics are used to compare performance to traditional machine learning models, such as Support Vector Machines (SVM), Random Forests (RF), and Multilayer Perceptions (MLP). The quantum SVM (QSVM) performs better in classification on both datasets, according to the results, indicating that quantum computing may be used to improve anomaly detection in cybersecurity applications.
Intrusion Detection Systems (IDS) rely on intelligent learning techniques to identify complex and evolving attack patterns within network traffic. This paper presents a comparative study of Support Vector Machines (SVM), Quantum Support Vector Machines (QSVM), and Variational Quantum Classifiers (VQC) in the context of intrusion detection. A unified evaluation framework is employed to compare these models based on feature representation, computational complexity, scalability, hardware requirements, and deployment feasibility. The analysis examines how QSVM and VQC utilize quantum feature mapping and parameterized quantum circuits to improve data representation capabilities. Nevertheless, their practical adoption remains limited by the constraints of current Noisy Intermediate-Scale Quantum (NISQ) devices, including hardware noise, restricted qubit resources, and scalability limitations. Conversely, SVM continues to be a dependable and scalable solution for present-day intrusion detection systems. The study further identifies the absence of a standardized framework for evaluating classical and quantum approaches as an important research gap. Overall, the findings suggest that hybrid quantum–classical learning frameworks provide the most realistic path toward adopting quantum machine learning for future cybersecurity solutions
Quantum computing presents potential advantages over classical computing in terms of computational complexity. Therefore, it is expected for quantum machine learning applications to have improvements in capacity and learning efficiency over classical machine learning methods. This paper aims to present a Systematic Literature Review of articles published between 2017 and 2022, identifying, analyzing, and comparing different proposals of quantum machine learning applications for network intrusion detection systems (IDS). This study focused on identifying papers that implemented quantum machine learning algorithms in the context of intrusion detection systems. The main algorithms found were variational hybrid quantum-classical, with models based on quantum support vector machines and quantum neural networks. Benefits compared to classical models were observed and described, such as reduced training time and improved classification accuracy for attacking traffic.
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.