论文部分内容阅读
检测分布式拒绝服务(Distributed Denial-of-Service,DDoS)攻击,需要将攻击流与正常流区分开来,特别是与繁忙业务流区分。检测方法需要高效的实现,使在线实时监测成为可能。在研究DDoS攻击对网络流量自相似性影响,加之对攻击流包特征分析的基础上,采用了一种联合小波分析与特征分析的检测DDoS攻击的方法。实验表明,这种新型检测方法比传统的检测方法准确。
Detecting Distributed Denial-of-Service (DDoS) attacks requires that the attack traffic be separated from the normal traffic, especially from the busy traffic flow. Detection methods need to be efficiently implemented, making online real-time monitoring possible. Based on the study of the influence of DDoS attacks on the self-similarity of network traffic and the analysis of the characteristics of attack flow packets, a method of detecting DDoS attacks using a combination of wavelet analysis and feature analysis is proposed. Experiments show that this new detection method is more accurate than the traditional detection methods.