基于改进Logistic回归算法的抗WebDDoS攻击模型的设计与实现  

Design and Implementation of Anti Web DDoS Attack Model Based on Improved Logistic Regression Algorithm

作　　者：张雪博 刘敬浩[1] 付晓梅[2] ZHANG Xuebo;LIU Jinghao;FU Xiaomei(School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300072, China;School of Marine Science and Technology, Tianjin University, Tianjin 300072, China)

机构地区：[1]天津大学电气自动化与信息工程学院,天津300072 [2]天津大学海洋科学与技术学院,天津300072

出　　处：《信息网络安全》2017年第6期62-67,共6页Netinfo Security

基　　金：国家自然科学基金[61571323]

摘　　要：Web DDoS攻击已经成为黑客常用的攻击手段之一。为了有效地提高Web DDoS攻击的检测速度和检测率,文章将量子粒子群优化方法与Logistic回归模型相结合,提出了一种轻量级检测新算法。该算法通过自适应的量子粒子群优化方法取代Newton法对Logistic回归系数进行求解,提高了回归系数的求解效率和精度。为了验证本算法的有效性,实验采用WorldC up98公开数据集对本算法与现有的改进Logistic回归算法的性能进行对比分析。实验结果表明,在Web DDoS攻击的检测方面,相比现有的改进Logistic回归算法,文章提出的算法能够获得更高的检测率以及更低的误检率,同时算法的时间复杂度与检测样本数量之间为线性关系。Web DDoS attack has become one of the common ways for hackers to attack.In order toimprove the detection speed and accuracy of Web DDoS attack effectively,this paper proposes a lightweight and novel detection algorithm combined quantum particle swarm optimization method withLogistic regression model.This algorithm replaces Newton method with adaptive swarm optimizationmethod to solve Logistic regression coeffi cient,improving the effi ciency and accuracy of solving theregression coeffi cient.In order to verify the availability of the proposed algorithm,the WorldCup98open dataset was used in our study to compare the performance of our algorithm with the existingimproved Logistic regression algorithms.The experimental results show that compared with the existingimproved Logistic regression algorithm,the proposed algorithm has higher detection rate and smallerdetection error rate in terms of detecting Web DDoS attacks.Meanwhile,there is a linear relationshipbetween the time complexity of the proposed algorithm and the number of detection sample.

关 键 词：WEB DDOS攻击检测 LOGISTIC回归 量子粒子群优化算法 牛顿法 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]