Network Attack Traffic Recognition Based on Quantum Neural Network

Zhang, Meng; Lv, Bo; Liu, Zi-shan

doi:10.1109/iccia55271.2022.9828461

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several studies considered the use of QML for the purpose of anomaly detection in computer networks. For instance, the Moore dataset [34] was used in [16] to train a single layer QNN, consisting of a single 2-qubit general unitary acting on every feature qubit and the result qubit. Similar to our approach, they produced a balanced dataset and normalized the feature values to be in the [0, 1] range, followed by a single-qubit binary encoding.…”

Section: Related Workmentioning

confidence: 99%

“…Recent studies [16] [17] [18] [19] have substantiated the efficacy of Quantum Neural Network (QNN) and Quantum Support Vector Machines (QSVM) in classifying network activities. These findings have demonstrated exceptionally high detection rates in noise-less simulation, showcasing the promise of quantum approaches in the field of network security and intrusion detection; however, none of them have shown good classification performance on a physical quantum computer.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Network Anomaly Detection Using Quantum Neural Networks on Noisy Quantum Computers

Kukliansky,

Orescanin,

Bollmann

et al. 2024

IEEE Trans. Quantum Eng.

View full text Add to dashboard Cite

The escalating threat and impact of network-based attacks necessitate innovative intrusion detection systems. Machine learning has shown promise, with recent strides in Quantum Machine Learning (QML) offering new avenues. However, the potential of quantum computing is tempered by challenges in current noisy intermediate-scale quantum (NISQ) era machines. In this study, we explore Quantum Neural Networks (QNNs) for intrusion detection, optimizing their performance within current quantum computing limitations. Our approach includes efficient classical feature encoding, QNN classifier selection, and performance tuning leveraging current quantum computational power. This study culminates in an optimized multi-layered QNN architecture for network intrusion detection. A small version of the proposed architecture was implemented on IonQ's Aria-1 quantum computer, achieving a notable 0.86 F1 score using the NF-UNSW-NB15 dataset. Additionally, we introduce a novel metric, certainty factor, laying the foundation for future integration of uncertainty measures in quantum classification outputs. Moreover, this factor is used to predict the noise susceptibility of our quantum binary classification system.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Network Anomaly Detection Using Quantum Neural Networks on Noisy Quantum Computers

Kukliansky,

Orescanin,

Bollmann

et al. 2024

IEEE Trans. Quantum Eng.

View full text Add to dashboard Cite

show abstract

“…O pré-processamento pode ser feito de maneiras distintas, mas todas abordam normalização e uma correção de erro nos conjuntos de dados de treinamento, seguida da codificação quântica. A codificação seguiu abordagens similares nos estudos de Payares e Martinez-Santos (2021), Kalinin e Krundyshev (2022) e Zhang et al (2022).…”

Section: Análise Dos Resultadosunclassified

Quantum Machine Learning for Network Intrusion Detection Systems, a Systematic Literature Review

Nicesio¹,

Leal²,

Gava³

19th CONTECSI International Conference on Information Systems and Technology Management

View full text Add to dashboard Cite

Quantum computing is a potential solution to several problems that classical computing faces such as computational time complexity. Quantum machine learning is therefore expected to have better runtime, capacity, and learning efficiency than classical methods offer. This article aims to present a systematic review of the state-of-the-art literature on quantum machine learning for cybersecurity in the specific application of network intrusion detection systems (IDS), identifying, analyzing, and correlating the different proposals for implementing quantum or hybrid algorithms. The methodology follows the Systematic Literature Review method, which, after its application, identified 5 articles that implemented quantum machine learning algorithms in the context of intrusion detection systems. The main algorithms were variational hybrid quantum-classical, with models based in quantum support vector machines and quantum neural networks. Benefits compared to purely classical models were observed and described, such as improved accuracy of attacking traffic data classification and reduced training time.

show abstract

Quantum Machine Learning for Network Intrusion Detection Systems, a Systematic Literature Review

Nicesio

Leal

Gava

2023

2023 IEEE 2nd International Conference on AI in Cybersecurity (ICAIC)

View full text Add to dashboard Cite

Network Attack Traffic Recognition Based on Quantum Neural Network

Cited by 4 publications

References 15 publications

Network Anomaly Detection Using Quantum Neural Networks on Noisy Quantum Computers

Network Anomaly Detection Using Quantum Neural Networks on Noisy Quantum Computers

Quantum Machine Learning for Network Intrusion Detection Systems, a Systematic Literature Review

Quantum Machine Learning for Network Intrusion Detection Systems, a Systematic Literature Review

Contact Info

Product

Resources

About