Skip to content

xuhuangchao/botnet-detection-with-ML

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

(1)/dataset-数据集
-原始数据集:ISCX-Botnet-2014 Dataset(https://www.unb.ca/cic/datasets/botnet.html)
[数据集大于100MB未上传]
-ISCX_Botnet-Training.pcap_Flow.csv: pcap文件经过cicflowmeter导出后的csv格式, Training和Testing分别为训练集和测试集

-training_label/testing_label.csv: 打标签0(正常)/1(恶意)后的数据集

-training/testing_label_protocoltype.csv: 按协议类型打标签0-4(No Attack/IRC/HTTP/P2P)后的数据集

-training/testing_label_attacktype.csv: 按攻击类型打标签0-5(其他/IRC/Neris/Rbot/Virut/Zeus)后的数据集

(2)/saved_model-最优模型
-decision-tree.pkl: 恶意/正常流量二分类的最优模型,使用决策树准确率可达81.14%
-random_forest_attacktype.pkl: 攻击类型多分类的最优模型,使用随机森林分类器准确率可达68.34%

(3)/src-代码
-运行Label.py输出training_label/testing_label.csv->classification.py
-运行Label_protocol_train/test.py输出training/testing_label_protocoltype.csv->classification_protocoltype.py
-运行Label_attacktype_train/test.py输出training/testing_label_attacktype.csv->classification_attacktype.py

About

春季学期态势感知实验

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages