基于SDN工业环境中的DDoS攻击检测  

DDoS Attack Detection Based on SDN Industrial Environment

作　　者：韩炎龙 翟亚红[1] 徐龙艳[1] Han Yanlong;Zhai Yahong;Xu Longyan(School of Electrical&Information Engineering,Hubei University of Automotive Technology,Shiyan 442002,China)

机构地区：[1]湖北汽车工业学院电气与信息工程学院,湖北十堰442002

出　　处：《湖北汽车工业学院学报》2023年第2期42-46,共5页Journal of Hubei University Of Automotive Technology

基　　金：湖北省教育厅科研计划重点项目(D20211802);湖北省科技厅重点研发计划项目(2022BEC008)。

摘　　要：针对基于软件定义网络(software defined network,SDN)架构的工业车间网络易受到DDoS攻击的问题,设计了检测防御模型。利用深度学习算法,融合卷积神经网络和双向长短期记忆网络,设计了CNN-BiLSTM模型,进行攻击检测,利用SDN设计防御策略,搭建基于SDN的工业车间网络平台进行仿真实验。结果表明:DDoS恶意流量检测准确率达到97%,并有效实现了DDoS攻击的防御。Since the industrial workshop network based on software defined network(SDN)architecture is vulnerable to distributed denial of service(DDoS)attacks,a detection and defense model was de‐signed.The deep learning algorithm combined with a convolutional neural networkand(CNN)a bidirec‐tional long short-term memory(BiLSTM)network was adopted,and a CNN-BiLSTM model was de‐signed to detect attacks.Defense strategies was designed based on SDN,and an industrial workshop net‐work platform based on SDN was built for simulation experiments.The results show that the detection accuracy of DDoS malicious traffic reaches over 97%,effectively defending against DDoS attacks.

关 键 词：软件定义网络 DDOS攻击 卷积神经网络 双向长短期记忆网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]