论文复现-《LUCID: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection》

这篇论文作者在github上有相对详细的指导。

一、搭建环境

1.在linux下安装miniconda，已经做好了。

2.创建一个新的conda环境，命名为python38，基于python3.8以及一些其他的包。注意拼写

conda create -n python38 python=3.8 numpy tensorflow=2.3.0 h5py lxml

3.激活这个新环境

conda activate python38

4.在补充安装一些包

(python38)$ pip3 install pyshark sklearn

 5.还要安装tshark，发现安装的版本过高，又进行卸载重装

apt-get install tshark

apt-get remove tshark

wget http://ftp.uni-kl.de/pub/wireshark/src/all-versions/wireshark-3.2.13.tar.xz

二、流量预处理

参考：R. Doriguzzi-Corin, S. Millar, S. Scott-Hayward, J. Martínez-del-Rincón and D. Siracusa, "Lucid: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection," in IEEE Transactions on Network and Service Management, vol. 17, no. 2, pp. 876-889, June 2020, doi: 10.1109/TNSM.2020.2971776.