基于随机森林与Bi-LSTM的5G网络切片攻击检测模型  

Research on 5G network slicing attack detection model based on random forest and Bi-LSTM

作　　者：尹龙润 张智斌[1] YIN Longrun;ZHANG Zhibin(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650504,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650504

出　　处：《陕西理工大学学报（自然科学版）》2024年第6期46-55,共10页Journal of Shaanxi University of Technology:Natural Science Edition

摘　　要：针对5G网络切片中的DoS和DDoS攻击这一关键安全挑战,研究了一种基于双向长短期记忆网络(Bi-LSTM)的攻击检测模型。该研究在模拟的5G切片平台上收集和分析攻击数据,揭示了现有方法在数据收集方面的不足,并在多个关键指标上展现了显著的相对增益。所提出的模型能够高效处理大规模数据集,并展现出快速的收敛速度。实验结果表明,该模型在检测准确率方面达到了99%,显著优于现有方法。这一发现不仅证明了所提方案的先进性,也对提升5G网络切片的安全性具有重要的实际应用价值。In addressing the key security challenges of denial of service(DoS)and distributed denial of service(DDoS)attacks in 5G network slicing,this study explores a detection model based on bidirectional long short-term memory networks(Bi-LSTM).The research involved collecting and analyzing attack data on a simulated 5G slicing platform,revealing inadequacies in data collection of existing methods and demonstrating significant relative gains across multiple key metrics.The proposed model efficiently processes large-scale datasets and shows rapid convergence speed.Experimental results indicate that the model achieves a detection accuracy rate of 99%,significantly surpassing existing methods.These findings not only prove the advanced nature of the proposed approach but also hold substantial practical application value in enhancing the security of 5G network slicing.

关 键 词：5G网络切片 DOS/DDOS攻击 攻击检测模型 双向长短期记忆网络 数据分析 

分 类 号：TN915.08[电子电信—通信与信息系统]