提出一种基于声音增强的通信网络入侵干扰检测方法,旨在提升网络入侵检测的准确性和实时性.通过分析网络流量产生的声音信号频谱,结合卷积神经网络(Convolutional Neural Network,CNN)与门控循环单元模型,增强关键频率特征,并检测入侵行为.实验结果表明,该方法对分布式拒绝服务(Distributed Denial of Service,DDoS)攻击、端口扫描等常见攻击类型的检测准确率超过 93%,误报率和漏报率均低于 3.5%,检测响应时间均在 30 ms以内,具有高效性与实用性.
Technology for Communication Network Intrusion Interference Detection Based on Sound Enhancement
A communication network intrusion detection method based on sound enhancement is proposed to improve the accuracy and real-time performance of network intrusion detection.By analyzing the spectrum of sound signals generated by network traffic,combining with the Convolutional Neural Network(CNN)and the gated cyclic unit model,the key frequency characteristics are enhanced and intrusion behavior is detected.Experimental results show that the detection accuracy of this method for common attacks such as Distributed Denial of Service(DDoS)attacks and port scanning is over 93%,the false positive rate and the false negative rate are both below 3.5%,and the detection response time is within 30 ms,so it is efficient and practical.
NETL
NSTL
万方数据
