Title: Design of DDoS attack detection system based on intelligent bee colony algorithm

Authors: Xueshan Yu; Dezhi Han; Zhenxin Du; Qiuting Tian; Gongjun Yin

Addresses: School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Information Engineering, Shanghai Maritime University, 1550 Pudong Avenue, Pudong New Area, Shanghai, Shanghai, 201306, China ' School of Computer Science, Sichuan University, No. 24, South Section, First Ring Road, Chengdu, Chengdu, 610065, Sichuan, China

Abstract: As the large data applications gain popularity, distributed denial of service (DDoS) has become increasingly a serious major network security issue. In response to the problem of DDoS attack detection in big data environment, a DDoS attack detection system based on traffic reduction and intelligent artificial bee colony algorithm (EABC_elite) is designed. The system combines the traffic reduction algorithm and the intelligent bee colony algorithm to reduce the data traffic according to the idea of abnormal extraction. It uses the traffic feature distribution entropy and the generalised likelihood comparison discrimination factor to jointly detect the characteristics of DDoS attack data streams in order to quickly and efficiently achieve DDoS attack data flow accuracy detection. The experimental results show that the demand of traffic detection in this system is greatly reduced, the algorithm time-consuming and DDoS detection accuracy are obviously better than the separate traffic reduction algorithm and traffic reduction algorithm combined with common artificial bee colony algorithm.

Keywords: distributed denial of service; DDoS attack; intelligent bee colony algorithm; traffic feature distribution entropy; traffic segmentation algorithm; generalised likelihood comparison.

DOI: 10.1504/IJCSE.2019.100243

International Journal of Computational Science and Engineering, 2019 Vol.19 No.2, pp.223 - 232

Received: 25 Apr 2018
Accepted: 02 Aug 2018
Published online: 20 Jun 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article