基于SVM-DT-MLP模型的Web日志异常流量检测研究

Research on Web Log Abnormal Traffic Detection Based on the SVM-DT-MLP Model

随着Web应用程序的普及,网络攻击和安全漏洞的风险日益增加。Web日志文件详细记录了网站运行信息,对日志中的流量进行分类从而检测出异常攻击流量是保障网页长期提供稳定、安全服务行之有效的方法之一。文中将Voting特征选择与Stacking集成相结合,构建了SVM-DT-MLP模型,并将其用于Web日志异常流量检测。测试结果表明,SVM-DT-MLP模型的性能显著优于单一算法模型,其Precision(精确度)达到92.44%,Recall(召回率)达到92.43%,F1-Score(F1值)达到92.44%。这意味着该模型能够有效地检测出异常攻击流量,并在保障网页提供稳定和安全服务方面具有很好的效果。

With the popularity of Web applications,the risk of cyber attacks and security vulnerabilities is increasing.Web log files record the running information of websites in detail.Classifying the traffic in logs to detect abnormal attack traffic is one of the effective methods to ensure the long-term stability and security service provided by Web pages.In this paper,Voting feature selection and the Stacking integration are combined to construct the SVM-DT-MLP model,and it is used to detect abnormal traffic in Web logs.The test results show that the performance of SVM-DT-MLP model is significantly better than that of the single algorithm model,with the precision reaching 92.44%,the recall reaching 92.43%and the F1-Score reaching 92.44%.This means that the model can effectively detect abnormal attack traffic and has a good effect in ensuring stable and secure services provided by Web pages.