期刊名称：International Journal of Network Security & Its Applications
印刷版ISSN：0975-2307
电子版ISSN：0974-9330
出版年度：2016
卷号：8
期号：6
页码：17
DOI：10.5121/ijnsa.2016.8502
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：When service system is under DDoS attacks, it is important to detect anomaly signature at starting time ofattack for timely applying prevention solutions. However, early DDoS detection is difficult task because thevelocity of DDoS attacks is very high. This paper proposes a DDoS attack detection method by modelingservice system as M/G/R PS queue and calculating monitoring parameters based on the model in odder toearly detect symptom of DDoS attacks. The proposed method is validated by experimental system and itgives good results.
