Performance of Botnet detection by neural networks in software-defined networks

The recent evolution of Internet to new paradigms such as network function virtual-ization and software defined networking poses new relevant challenges to the detection of Botnet attacks, calling for innovative approaches. In this work we propose a detection mechanism based on an Artificial Neural Net classifier trained by available data sets collected in conventional networks. We apply such detection mechanism to the timely use case scenario of a software defined network infected by the dangerous Botnet Mirai, circulating in October 2016. Experimental results show an accuracy of Botnet detection higher than 99%, thus outperforming available Botnet detection mechanisms currently used in conventional networks.