基于Web行为轨迹的应用层DDoS攻击防御模型

发布时间：2018-04-30 12:34

本文选题：分布式拒绝服务攻击 + 应用层　；参考：《计算机应用》2017年01期

【摘要】：为了有效防御应用层分布式拒绝服务攻击(DDoS),定义了一种搭建在Web应用服务器上的基于Web行为轨迹的防御模型。把用户的访问行为抽象为Web行为轨迹,根据攻击请求的生成方式与用户访问Web页面的行为特征,定义了四种异常因素,分别为访问依赖异常、行为速率异常、轨迹重复异常、轨迹偏离异常。采用行为轨迹化简算法简化行为轨迹的计算,然后计算用户正常访问网站时和攻击访问时产生的异常因素的偏离值,来检测针对Web网站的分布式拒绝服务攻击,在检测出某用户产生攻击请求时,防御模型禁止该用户访问来防御DDoS。实验采用真实数据当作训练集,在模拟不同种类攻击请求下,防御模型短时间识别出攻击并且采取防御机制抵制。实验结果表明,Web行为轨迹的防御模型能够有效防御针对Web网站的分布式拒绝服务攻击。
[Abstract]:In order to effectively protect DDoS from distributed denial of service (DDoS) attacks in application layer, a defense model based on Web behavior trajectory is defined on Web application server. The user's access behavior is abstracted as Web behavior trajectory. According to the generation of attack request and the behavior characteristics of user visiting Web page, four kinds of abnormal factors are defined: access dependent exception, behavior rate exception, track repeat anomaly. The trajectory deviates from the anomaly. The behavior trajectory simplification algorithm is used to simplify the calculation of the behavior trajectory, and then the deviations of the abnormal factors generated when the user visits the website normally and attacks are calculated to detect the distributed denial-of-service attacks against the Web sites. When an attack request is detected by a user, the defense model forbids the user from accessing it to defend against DDoS. Using real data as the training set, the defense model can identify attacks and resist them in a short time under the condition of simulating different kinds of attack requests. The experimental results show that the defense model of web behavior trajectory can effectively protect against distributed denial of service (DDoS) attacks against Web sites.
【作者单位】：中国矿业大学计算机科学与技术学院;
【分类号】：TP393.08

【相似文献】