基于决策树算法的Web网站攻击检测方法

Web Site Attack Detection Method Based on Decision Tree Algorithm

为了更好地识别Web网站攻击,笔者提出一种基于决策树算法的Web网站攻击检测方法.该方法通过决策树归纳算法,训练样本集将网站分为合法网站和Web攻击网站;同时,为了度量Web攻击网站检测指标,更好地寻找一种检测Web网站攻击算法,引入检测时间度量指标.实验结果表明,在不影响用户使用网站的前提下,能够快速识别Web攻击网站.将该方法与贝叶斯算法、朴素贝叶斯算法进行对比,发现在正确率、精确率和召回率3个对比指标下,决策树算法在一定程度上优于其他算法.实验结果表明,该方法对Web攻击网站的检测识别具有很高的效率.

A Web attack detection method based on decision tree algorithm is proposed in this paper in order to better identify Web attacks.This method divides Websites into legal Websites and Web attack through decision tree induction algorithm and training sample set.What's more,in order to measure the detection index of Web attack and better find a detection algorithm for Web attack,the detection time measurement index is introduced.The experimental results show that the detection time measurement index can quickly identify Web attack Websites without affecting the use of Websites.Comparing this method with Bayesian algorithm and Naive Bayesian algorithm,it is found that the decision tree algorithm is superior to other algorithms to a certain extent under the three comparison indexes of accuracy rate,precision rate and recall rate.The experimental results show that the method has good effect and efficiency on the detection and identification of Web attack.