Botnet DGA Dataset

This is the dataset used in our journal paper, submitted to: IEEE Transactions on Dependable and Secure Computing, Special Issue on Explainable Artificial Intelligence for Cyber Threat Intelligence (XAI-CTI) Applications.

Submitted = 12-Jan-2021 (under review)
ID = TDSCSI-2021-01-0045

Size: 205 MB

Platform: all platform (csv file)

Environment: all environment (csv file)

Major component description: We adopted Patsakis’ approach on the dataset used in [82], using Alexa top 1M domains and 10 botnet DGAs (total 1.803.333 domain names) published by Abakumov as the ground truth dataset for botnet detection ( https://github.com/andrewaeva/DGA). This dataset contains columns: a CharLength, TreeNewFeature, nGramReputation_Alexa, REAlexa, MinREBotnets, Entropy and InformationRadius. Please read our paper to understand how we calculate it.

Detailed setup instructions: Copy the csv file and use it as your need.

Detailed run instructions: Please note that the columns are = Entropy,REAlexa,MinREBotnets,InformationRadius,CharLength,TreeNewFeature,nGramReputation_Alexa,Class

Output description: Botnet DGA dataset

Contact information: Hatma Suryotrisongko

http://keamanansiber.id/

https://github.com/keamanansiber/