Research on 5G network slicing attack detection model based on random forest and Bi-LSTM
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.
5G network slicingdenial of service attacksattack detection modelbidirectional long short-term memory networks(Bi-LSTM)data analysis
万方数据
维普
