基于多尺度卷积神经网络的DDoS攻击检测方法

DDoS Attack Detection Method Based on Multi-scale Convolutional Neural Network

近年来,网络安全面临着日益严峻的挑战,其中分布式拒绝服务(DDoS)攻击是网络威胁中的一种常见形式。为了应对这一挑战,提出了一种基于多尺度卷积神经网络(MSCNN)的DDoS攻击检测方法。在CICDDoS2019day1数据集训练模型,CICDDoS2019day2数据集测试模型检测性能。通过利用MSCNN对网络流量进行预测和分类,能够有效识别DDoS攻击并减少误报率。实验表明,MSCNN方法在准确性、召回率、F1得分性能指标上优于SVM、DNN、CNN、LSTM和GRU。

In recent years,network security is facing increasing challenges,among which Distributed Denial of Service(DDoS)attack is a common form of network threats.In order to deal with this challenge,this paper proposes a DDoS attack detection method based on Multi-scale Convolutional Neural Network(MSCNN).The model is trained on the CICDDoS2019day1 dataset,and the model detection performance is tested on the CICDDoS2019day2 dataset.By using MSCNN to predict and classify network trafic,DDoS attacks can be effectively identified and false positive rate can be reduced.Experiments show that the MSCNN method is superior to DNN,CNN and LSTM in terms of accuracy,recall and F1 score performance metrics.