Detail aplikovaného výsledku

DGA Hunter

BUČKO, F.; HRANICKÝ, R.

Original Title

DGA Hunter

English Title

DGA Hunter

Type

Software

Abstract

DGA Hunter is a Django-based web application that can detect and categorize domains generated by DGA algorithms to reveal hidden botnet communication channels. The application achieves high detection accuracy by using advanced machine learning techniques and two integrated classifiers. The binary classifier is able to detect whether a domain name is of algorithmic origin. The second, multiclass classifier, is then able to detect the probable DGA family.

Abstrakt aglicky

DGA Hunter is a Django-based web application that can detect and categorize domains generated by DGA algorithms to reveal hidden botnet communication channels. The application achieves high detection accuracy by using advanced machine learning techniques and two integrated classifiers. The binary classifier is able to detect whether a domain name is of algorithmic origin. The second, multiclass classifier, is then able to detect the probable DGA family.

Keywords

Botnet, DGA, Detection, Classification, C&C, Feature engineering, XGBoost

Key words in English

Botnet, DGA, Detection, Classification, C&C, Feature engineering, XGBoost

Location

Aplikace je ke stažení v přiložených souborech.

Licence fee

In order to use the result by another entity, it is always necessary to acquire a license

www

Documents

Responsibility: Ing. Marek Strakoš