Xander: un ensamble cuántico-clásico para la detección de intrusiones avanzadas en redes modernas
DOI:
https://doi.org/10.59722/riic.v3i2.1233Palavras-chave:
Aprendizagem automática quântica, sistemas de deteção de intrusões, modelos híbridos, NISQ, cibersegurança.Resumo
A crescente complexidade das ameaças cibernéticas exige sistemas de deteção de intrusões capazes de processar tráfego de rede dinâmico e de grande dimensão. Embora os métodos clássicos de aprendizagem automática tenham alcançado um excelente desempenho neste domínio, continuam a enfrentar limitações relacionadas com a escalabilidade, a adaptabilidade e a robustez face a padrões de ataque em constante evolução. A aprendizagem automática quântica revelou-se uma alternativa promissora; no entanto, os processadores quânticos atuais impõem limitações práticas relacionadas com o ruído, a disponibilidade limitada de qubits, a decoerência e a profundidade dos circuitos.
Este artigo apresenta o Xander, uma arquitetura híbrida em conjunto quântico-clássico para a deteção de intrusões em redes sob as restrições da era NISQ. A estrutura proposta integra modelos quânticos, incluindo componentes de máquinas de vetores de suporte quânticos, classificadores quânticos variacionais e redes neurais convolucionais quânticas, com modelos clássicos como Random Forest, XGBoost e perceptrões multicamadas.
Estes modelos são combinados através de um mecanismo otimizado de votação suave ponderada e complementados por uma estratégia de backup dinâmica concebida para reduzir o impacto dos resultados quânticos instáveis. As experiências foram realizadas utilizando subconjuntos reduzidos e pré-processados dos conjuntos de dados CIC-IDS-2017 e CIC-IDS-2018, aplicando a análise de componentes principais, para permitir a codificação de características compatíveis com a computação quântica.
A estrutura foi avaliada através de simulação clássica, simulação quântica e execução em hardware quântico real. Os resultados mostram que a abordagem híbrida atinge um elevado desempenho de classificação e mantém um comportamento estável sob o ruído induzido pelo hardware, alcançando um desempenho competitivo. As conclusões sugerem que os modelos híbridos constituem uma via prática para integrar a computação quântica em aplicações de cibersegurança sem exigir uma vantagem quântica a curto prazo.
Downloads
Referências
Abdulrazzaq Altarraji, M. A., & Mokdad, A. (2024). Quantum-Assisted Machine Learning for Enhanced Fraud Detection in Cybersecurity. International Research Journal of Innovations in Engineering and Technology, 08(05),319 – 324. https://doi.org/10.47001/IRJIET/2024.805042
Abreu, D., Rothenberg, C. E., & Abelem, A. (2024). QML-IDS: Quantum Machine Learning Intrusion Detection System. Proceedings - IEEE Symposium on Computers and Communications. https://doi.org/10.1109/ISCC61673.2024.10733655
Ajdani, M. (2025). Deep Learning-Based Intrusion Detection Systems: A Novel Approach Using Generative Adversarial Networks (GANs). International Journal of Information Security and Privacy (IJISP), 19(1), 1-15. https://doi.org/10.4018/IJISP.383299
Akif, M. A., Butun, I., Williams, A., & Mahgoub, I. (2025). Hybrid Machine Learning Models for Intrusion Detection in IoT: Leveraging a Real-World IoT Dataset (No. arXiv:2502.12382). arXiv. https://doi.org/10.48550/arXiv.2502.12382
Alluhaibi, R. (2024). Quantum Machine Learning for Advanced Threat Detection in Cybersecurity. International Journal of Safety and Security Engineering, 14(3), 875–883. https://doi.org/10.18280/IJSSE.140319
Almseidin, M., Alzubi, M., Kovacs, S., & Alkasassbeh, M. (2018). Evaluation of Machine Learning Algorithms for Intrusion Detection System (No. arXiv:1801.02330). arXiv. https://doi.org/10.48550/arXiv.1801.02330
Alotaibi, A., & Rassam, M. A. (2023). Adversarial Machine Learning Attacks against Intrusion Detection Systems: A Survey on Strategies and Defense. Future Internet, 15(2), 62. https://doi.org/10.3390/fi15020062
Camargo, J. A. F., Aguilar, J., & Pinto, Á. (2024, agosto). Analysis of Quantum Support Vector Machines in Classification Problems. https://doi.org/10.1109/CLEI64178.2024.10700573
Cerezo, M., Arrasmith, A., Babbush, R., Benjamin, S. C., Endo, S., Fujii, K., McClean, J. R., Mitarai, K., Yuan, X., Cincio, L., & Coles, P. J. (2021). Variational quantum algorithms. Nature Reviews Physics, 3(9), 625–644. https://doi.org/10.1038/s42254-021-00348-9
Chen, Z., Zhu, Z., & Li, X. (2025). Cyber threat detection enabled by quantum computing. arXiv preprint arXiv:2512.18493. https://doi.org/10.48550/arXiv.2512.18493
Danso, P. K., Neto, E. C. P., Dadkhah, S., Zohourian, A., Molyneaux, H., & Ghorbani, A. A. (2022). Ensemble-based Intrusion Detection for Internet of Things Devices. 2022 IEEE 19th International Conference on Smart Communities (HONET), 034–039. https://doi.org/10.1109/HONET56683.2022.10019140
Dong, Y., Hu, W., Zhang, J., Chen, M., Liao, W., & Chen, Z. (2022). Quantum beetle swarm algorithm optimized extreme learning machine for intrusion detection. Quantum Information Processing, 21(1), 9. https://doi.org/10.1007/s11128-021-03311-w
Elsedimy, E. I., Elhadidy, H., & Abohashish, S. M. M. (2024). A novel intrusion detection system based on a hybrid quantum support vector machine and improved Grey Wolf optimizer. Cluster Computing, 27(7), 9917–9935. https://doi.org/10.1007/s10586-024-04458-8
Fan, F., Shi, Y., Guggemos, T., & Zhu, X. X. (2024). Hybrid Quantum-Classical Convolutional Neural Network Model for Image Classification. IEEE Transactions on Neural Networks and Learning Systems, 35(12), 18145–18159. https://doi.org/10.1109/TNNLS.2023.3312170
Farhi, E., & Neven, H. (2018). Classification with Quantum Neural Networks on Near Term Processors (No. arXiv:1802.06002). arXiv. https://doi.org/10.48550/arXiv.1802.06002
Ganapathi, P., & Shanmugapriya, D. (2019). Handbook of research on machine and deep learning applications for cyber security. IGI Global. ISBN: 9781522596106 Disponible en: https://books.google.com/books?id=vK2rDwAAQBAJ
Gong, C., Guan, W., Gani, A., & Qi, H. (2022). Network attack detection scheme based on variational quantum neural network. The Journal of Supercomputing, 78(15), 16876–16897. https://doi.org/10.1007/s11227-022-04542-z
Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., & Gambetta, J. M. (2019). Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747), 209–212. https://doi.org/10.1038/s41586-019-0980-2
Hozouri, A., Mirzaei, A., & Effatparvar, M. (2025). A comprehensive survey on intrusion detection systems with advances in machine learning, deep learning and emerging cybersecurity challenges. Discover Artificial Intelligence, 5(1), 314. https://doi.org/10.1007/s44163-025-00578-1
Kadry, H., Farouk, A., Zanaty, E. A., & Reyad, O. (2023). Intrusion detection model using optimized quantum neural network and elliptical curve cryptography for data security. Alexandria Engineering Journal, 71, 491–500. https://doi.org/10.1016/j.aej.2023.03.072
Kalinin, M., & Krundyshev, V. (2023). Security intrusion detection using quantum machine learning techniques. Journal of Computer Virology and Hacking Techniques, 19(1), 125–136. https://doi.org/10.1007/s11416-022-00435-0
Kalyan, B. K. P., Chandana, M. S., Karimalla, N., & Bukaita, W. (2025). Generative Adversarial Network–based Intrusion Detection for Securing In-vehicle Communication in Electric Vehicles. American Journal of Information Science and Technology, 9(4), 304–323. https://doi.org/10.11648/j.ajist.20250904.16
Khan, F. A., Gumaei, A., Derhab, A., & Hussain, A. (2019). A Novel Two-Stage Deep Learning Model for Efficient Network Intrusion Detection. IEEE Access, 7, 30373–30385. https://doi.org/10.1109/ACCESS.2019.2899721
Khan, N., Mohmand, M. I., Rehman, S. ur, Ullah, Z., Khan, Z., & Boulila, W. (2024). Advancements in intrusion detection: A lightweight hybrid RNN-RF model. PLoS One, 19(6). https://doi.org/10.1371/journal.pone.0299666
Kim, T. H., & Madhavi, S. (2024). Quantum intrusion detection system using outlier analysis. Scientific Reports, 14(1), 27114. https://doi.org/10.1038/s41598-024-78389-0
Li, D., Chen, D., Shi, L., Jin, B., Goh, J., & Ng, S.-K. (2019). MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks (No. arXiv:1901.04997). arXiv. https://doi.org/10.48550/arXiv.1901.04997
Maseer, Z. K., Yusof, R., Al-Bander, B., Saif, A., & Kadhim, Q. K. (2023). Meta-Analysis and Systematic Review for Anomaly Network Intrusion Detection Systems (No. arXiv:2308.02805). arXiv. https://doi.org/10.48550/arXiv.2308.02805
Metawei, M. A., Said, H., Taher, M., Eldeib, H., & Nassar, S. M. (2020). Survey on Hybrid Classical-Quantum Machine Learning Models. 2020 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI), 1–6. https://doi.org/10.1109/CCCI49893.2020.9256649
Musa, U. S., Chhabra, M., Ali, A., & Kaur, M. (2020). Intrusion Detection System using Machine Learning Techniques: A Review. 2020 International Conference on Smart Electronics and Communication (ICOSEC), 149–155. https://doi.org/10.1109/ICOSEC49089.2020.9215333
Nazim, S., Hussain, S. S., Yousuf, B., Sultana, S., & Tanweer, E. (2025). An innovative intrusion detection framework using GAN-augmented Deep Ensemble Neural Network for cross-domain IoT–cloud security. Internet of Things, 34, 101773. https://doi.org/10.1016/j.iot.2025.101773
Nicesio, O. K., Leal, A. G., & Gava, V. L. (2023). Quantum Machine Learning for Network Intrusion Detection Systems, a Systematic Literature Review. 2023 IEEE 2nd International Conference on AI in Cybersecurity (ICAIC). https://doi.org/10.1109/ICAIC57335.2023.10044125
Noor, K., Agbotiname, L. I., Chun-Ta, L., & Chi-Yao, W. (2025). A Review of Machine Learning and Transfer Learning Strategies for Intrusion Detection Systems in 5G and Beyond. Mathematics, 13(7). https://doi.org/10.3390/math13071088
Noor, M., Abbas, H., & Shahid, W. B. (2018). Countering cyber threats for industrial applications. Journal of Network and Computer Applications, 103, 249–261. https://doi.org/10.1016/j.jnca.2017.10.004
Odeh, A., & Abu Taleb, A. (2023). Ensemble-Based Deep Learning Models for Enhancing IoT Intrusion Detection. Applied Sciences, 13(21), 11985. https://doi.org/10.3390/app132111985
Orazi, F., Gasperini, S., Lodi, S., & Sartori, C. (2024). Hybrid Quantum Technologies for Quantum Support Vector Machines. Information, 15(2), 72. https://doi.org/10.3390/info15020072
Pinto, A., Herrera, L.-C., Donoso, Y., & Gutierrez, J. A. (2023). Survey on Intrusion Detection Systems Based on Machine Learning Techniques for the Protection of Critical Infrastructure. Sensors, 23(5), 2415. https://doi.org/10.3390/s23052415
Premalatha, D. V. (2025). Ensemble-Based Intrusion Detection for IoT Networks Using the CICIoT2023 Dataset. Journal of Information Systems Engineering and Management, 10(21s), 743–755. https://doi.org/10.52783/jisem.v10i21s.3407
Rawat, S., Srinivasan, A., Ravi, V., & Ghosh, U. (2022). Intrusion detection systems using classical machine learning techniques vs integrated unsupervised feature learning and deep neural network. Internet Technology Letters, 5(1). https://doi.org/10.1002/ITL2.232
Rehman, H. M. R. U., Liaquat, S., Gul, M. J., Jhandir, M. Z., Gavilanes, D., Vergara, M. M., & Ashraf, I. (2025). A systematic literature study of machine learning techniques based intrusion detection. Journal of Big Data, 12(1), 264. https://doi.org/10.1186/s40537-025-01323-2
Sarker, I. H. (2021). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science, 2(3), 160. https://doi.org/10.1007/s42979-021-00592-x
Sharafaldin, I., Habibi Lashkari, A., & Ghorbani, A. A. (2018). Toward Generating a New Intrusion Detection Dataset. Proceedings of the 4th International Conference on Information Systems Security and Privacy, 108–116. https://doi.org/10.5220/0006639801080116
Shen, J.-Y., Wu, C.-H., Hua, C.-Y., Chang, M.-H., Kuo, S.-Y., Chou, Y.-H., & Kuo, S.-Y. (2024). An Efficient Quantum-inspired Computing Approach for Intrusion Detection System. 2024 IEEE 24th International Conference on Nanotechnology (NANO), 306–310. https://doi.org/10.1109/NANO61778.2024.10628664
Solar, M., Alvarez, F. C., Villacura, J.-P., & Dombrovskaia, L. (2024). A Review on Quantum Machine Learning and Quantum Cryptography. Memoria Investigaciones En Ingeniería, 27, 180–199. https://doi.org/10.36561/ING.27.12
Talukder, Md. A., Hasan, K. F., Islam, Md. M., Uddin, Md. A., Akhter, A., Yousuf, M. A., Alharbi, F., & Moni, M. A. (2023). A dependable hybrid machine learning model for network intrusion detection. Journal of Information Security and Applications, 72, 103405. https://doi.org/10.1016/j.jisa.2022.103405
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
