Abstract

It is proposed to use the mathematical apparatus of wavelet transforms combined with the clustering of the obtained and transformed coefficients to detect attacks in the traffic of backbone networks. The wavelet transform coefficients obtained from the parameters of network packets are checked for the degree of multiple dependence, on the basis of which the standard deviation is calculated and the resulting coefficients are clustered to identify anomalies of the investigated network flow. The efficiency of the proposed method is confirmed by the results of experiments on detecting denial of service attacks.

中文翻译：

---

基于数理统计和人工智能方法的大规模网络分布式拒绝服务攻击检测

摘要

提出使用小波变换的数学装置结合获得的和变换后的系数的聚类来检测骨干网流量中的攻击。检查从网络数据包的参数获得的小波变换系数的多重依赖程度，在此基础上计算标准偏差，并对所得系数进行聚类以识别所研究网络流量的异常情况。通过检测拒绝服务攻击的实验结果证实了该方法的有效性。