Národní úložiště šedé literatury Nalezeno 1 záznamů.  Hledání trvalo 0.01 vteřin. 
Classification of Domain Names Generated by DGA
Bučko, Filip ; Žádník, Martin (oponent) ; Hranický, Radek (vedoucí práce)
The DGA (Domain Generation Algorithm) is a technique that allows malware to receive commands from an attacker while avoiding detection. The main objective of this thesis is to build a system for the detection and classification of DGA domains in order to uncover malicious communication. For the purpose of detection, a binary classifier based on machine learning is designed and implemented in this work. Classification plays a crucial role in the automated analysis of malware and thus ensures proactive defense. Additionally, 4 classifiers based on different approaches are introduced for the classification of domains into DGA families. Subsequently, the advantages and disadvantages of presented approaches are identified. The final implementation of multi-class classification consists of a combination of classifiers that provide the best results. Furthermore, this work identifies characteristics specific to DGA domains that are necessary for the creation of classifiers. Testing the resulting implementation of classifiers demonstrates high accuracy in both DGA domain detection and classification.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.