DDoS Attacks Detection Algorithm Based on Flow Connection Entropy
Zhang Jian · Jisuanji gongcheng · 2007
On the basis of analyzing the features of distributed denial of service(DDoS) attacks,flow connection entropy time series analysis is proposed.It uses non-parametric CUSUM algorithm to complete the detection task of DDoS attacks.It minimizes the average delay of detection for a given false alarm rate.It has better detection effect on the fixed source IP and random destination ports’s DDoS.Experimental result demonstrates this model can detect DDoS attack as early as possible with high detection accuracy.