| 1 | 0 | 23 |
| 下载次数 | 被引频次 | 阅读次数 |
随着网络规模的扩大和攻击手段的复杂化，传统网络异常检测方法在处理高维、非线性数据时面临效率低、准确率不足等问题，因此提出了基于量子聚类算法的网络异常检测协同模型，通过量子力学原理与经典机器学习深度融合，提升复杂网络环境下的异常检测能力。该模型采用改进的自适应量子势能函数，设计量子编码策略实现网络流量特征的降维增强，构建量子-经典协同处理框架，形成动态反馈优化机制。在NSL-KDD数据集上的实验表明，该模型准确率、F1值和召回率均有提升，满足大规模网络实时处理需求。研究结果为网络安全领域提供了新的量子启发式解决方案，并为量子机器学习在复杂场景下的应用提供了理论和技术参考。
Abstract：Traditional network anomaly detection methods faces problems such as low efficiency or accuracy when dealing with high-dimensional and nonlinear data in the era when network scale has greatly expanded and network attack become sophisticated. Therefore, this paper proposes a collaborative network anomaly detection model based on quantum clustering algorithm, which could improve detection ability in complex network environments with the help of deep integration of quantum mechanics principles and classical machine learning. The model, by adopting an improved adaptive quantum potential function, designs a quantum coding strategy to realize dimensionality reduction enhancement of network traffic features, and constructs a quantum-classical collaborative processing framework to achieve a dynamic feedback optimization mechanism. Experiments on the NSL-KDD dataset show improved accuracy, F1-score and recall rate with the model, which is qualified for real-time processing of large-scale networks. The research results provide a new quantum-inspired solution for the field of network security, and offer theoretical and technical references for the application of quantum machine learning in complex scenarios.
[1]Liu R,Shi J,Chen X,et al.Network anomaly detection and security defense technology based on machine learning:A review[J].Computers and Electrical Engineering,2024,119:109581.
[2]Schummer P,Del Rio A,Serrano J,et al.Machine learning-based network anomaly detection:Design,implementation,and evaluation[J].Ai,2024,5(4):2967-2983.
[3]Baisholan N,Baisholanova K,Kubayev K,et al.Corporate network anomaly detection methodology utilizing machine learning algorithms[J].Smart Science,2024,12(4):666-678.
[4]Tu B,Wang Z,Yang X,et al.Hyperspectral anomaly detection using quantum potential clustering[J].IEEE Transactions on Instrumentation and Measurement,2022,71:5025913.
[5]王健，张蕊，姜楠.量子机器学习综述[J].软件学报，2024,35(8):3843-3877.
[6]刘晓楠，宋慧超，王洪，等.Grover算法改进与应用综述[J].计算机科学，2021,48(10):315-323.
[7]Chen L,Li T,Chen Y,et al.Design and analysis of quantum machine learning:A survey[J].Connection Science,2024,36(1):2312121.
[8]Gopalakrishnan D,Dellantonio L,Di Pilato A,et al.qCLUE:A quantum clustering algorithm for multi-dimensional datasets[J].Frontiers in Quantum Science and Technology,2024,3:1462004.
[9]Patil S,Banerjee S,Panigrahi P K.NISQ-friendly measurement-based quantum clustering algorithms[J].Quantum Information Processing,2024,23(10):341.
[10]Hdaib M,Rajasegarar S,Pan L.Quantum deep learning-based anomaly detection for enhanced network security[J].Quantum Machine Intelligence,2024,6(1):26.
[11]刘翔，祝静，仲国强，等.量子原型聚类[J].计算机科学，2023,50(8):27-36.
[12]左进，陈泽茂.基于改进K均值聚类的异常检测算法[J].计算机科学，2016,43(8):258-261.
[13]杨晓晖，张圣昌.基于多粒度级联孤立森林算法的异常检测模型[J].通信学报，2019,40(8):133-142.
[14]Lindemann B,Maschler B,Sahlab N,et al.A survey on anomaly detection for technical systems using LSTM networks[J].Computers in Industry,2021,131:103498.
[15]Rangan K K,Abou Halloun J,Oyama H,et al.Quantum computing and resilient design perspectives for cybersecurity of feedback systems[J].IFAC-Papers On Line,2022,55(7):703-708.
[16]Ikram S T,Cherukuri A K,Poorva B,et al.Anomaly detection using XGBoost ensemble of deep neural network models[J].Cybernetics and Information Technologies,2021,21(3):175-188.
基本信息:
DOI：10.16856/j.cnki.52-1142/n.2026.01.011
中图分类号:TP393.08;TP18;O413
引用信息:
[1]黄谊拉,刘敏.基于量子聚类算法的网络异常检测模型研究[J].贵阳学院学报(自然科学版),2026,21(01):98-103.DOI:10.16856/j.cnki.52-1142/n.2026.01.011.
基金信息:
安徽省级质量工程项目(2022tsgsp037)
2026-03-30
2026-03-30