The dataset contains Normal, DGA and Tunneling domain names: i. the total number of normal domains are conformed by the Alexa top one million domains, 3,161 normal domains provided by the Bambenek Consulting feed, and another 177,017 normal domains; ii. the DGA domains were obtained from the repositories of DGA domains of Andrey Abakumov and John Bambenek, corresponding to 51 different malware families; iii. the DNS Tunneling consist of 8000 tunnel domains generated using a set of well known DNS tunneling tools under laboratory conditions: iodine, dnscat2 and dnsExfiltrator. The dataset is described in the paper: Palau, F., Catania, C., Guerra, J., García, S. J., & Rigaki, M. (2019). Detecting DNS threats: A deep learning model to rule them all. In XX Simposio Argentino de Inteligencia Artificial (ASAI 2019)-JAIIO 48 (Salta).

The paper where the dataset is discussed can be found at http://sedici.unlp.edu.ar/handle/10915/87859