《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (12): 3775-3784.DOI: 10.11772/j.issn.1001-9081.2021091653

• 网络空间安全 • 上一篇    

基于集成学习的多类型应用层DDoS攻击检测方法

李颖之(), 李曼, 董平, 周华春   

  1. 北京交通大学 电子信息工程学院,北京 100044
  • 收稿日期:2021-09-22 修回日期:2022-01-14 接受日期:2022-01-28 发布日期:2022-12-21 出版日期:2022-12-10
  • 通讯作者: 李颖之
  • 作者简介:李曼(1997—),女,河南濮阳人,博士研究生,主要研究方向:网络安全、智能通信
    董平(1979—),男,北京人,教授,博士,主要研究方向:新一代互联网、智慧车联网、移动互联网
    周华春(1965—),男,北京人,教授,博士,主要研究方向:智能通信、移动互联网、网络安全、卫星网络。
  • 基金资助:
    国家重点研发计划项目(2018YFA0701604)

Multi‑type application‑layer DDoS attack detection method based on integrated learning

Yingzhi LI(), Man LI, Ping DONG, Huachun ZHOU   

  1. College of Electronic Information Engineering,Beijing Jiaotong University,Beijing 100044,China
  • Received:2021-09-22 Revised:2022-01-14 Accepted:2022-01-28 Online:2022-12-21 Published:2022-12-10
  • Contact: Yingzhi LI
  • About author:LI Man, born in 1997, Ph. D. candidate. Her research interests include cyber security, intelligent communication.
    DONG Ping, born in 1979, Ph. D., professor. His research interests include next generation Internet, smart Internet of vehicles,mobile Internet.
    ZHOU Huachun, born in 1965, Ph. D., professor. His research interests include intelligent communication, mobile Internet, network security, satellite network.
  • Supported by:
    National Key Research and Development Program of China(2018YFA0701604)

摘要:

针对应用层分布式拒绝服务(DDoS)攻击类型多、难以同时检测的问题,提出了一种基于集成学习的应用层DDoS攻击检测方法,用于检测多类型的应用层DDoS攻击。首先,数据集生成模块模拟正常和攻击流量,筛选并提取对应的特征信息,并生成表征挑战黑洞(CC)、HTTP Flood、HTTP Post及HTTP Get攻击的47维特征信息;其次,离线训练模块将处理后的有效特征信息输入集成后的Stacking检测模型进行训练,从而得到可检测多类型应用层DDoS攻击的检测模型;最后,在线检测模块通过在线部署检测模型来判断待检测流量的具体流量类型。实验结果显示,与Bagging、Adaboost和XGBoost构建的分类模型相比,Stacking集成模型在准确率方面分别提高了0.18个百分点、0.21个百分点和0.19个百分点,且在最优时间窗口下的恶意流量检测率达到了98%。验证了所提方法对多类型应用层DDoS攻击检测的有效性。

关键词: 多类型, 应用层分布式拒绝服务攻击, 分布式拒绝服务, 机器学习, 集成学习

Abstract:

Aiming at the problem of multiple types of application?layer Distributed Denial of Service (DDoS) attacks, which are difficult to detect simultaneously, an application?layer DDoS attack detection method based on integrated learning was proposed to detect multiple types of application?layer DDoS attacks. Firstly, by using the dataset generation module, the normal and attack traffic was simulated, the corresponding feature information was filtered and extracted, and 47?dimensional feature information characterized Challenge Collapsar (CC), HTTP Flood, HTTP Post and HTTP Get attacks were generated. Secondly, by using the offline training module, the effective features were processed and input into the integrated Stacking detection model for training, thereby obtaining a detection model that can detect multiple types of application?layer DDoS attacks. Finally, by using the online detection module, the specific traffic type of the traffic to be detected was judged through deploying the detection model online. Experimental results show that compared with the classification models constructed by Bagging,Adaboost and XGBoost,the Stacking integretion model improves the accuracy by 0. 18 percentage points,0. 21 percentage points and 0. 19 percentage points respectively,and has the malicious traffic detection rate reached 98% under the optimal time window. It can be seen that the proposed method has good performance in detecting multi-type application-layer DDoS attacks.

Key words: multi?type, application?layer Distributed Denial of Service (DDoS) attack, Distributed Denial of Service (DDoS), machine learning, integrated learning

中图分类号: