A Botnet Detection Method on SDN using Deep Learning

The increased amount of user damage caused by malware is becoming a serious problem. Network software has also been advancing, and potentially it can be utilized to counter malware. In this work, we analyze the traffic data of malware collected from an existing network and classify normal traffic and malicious traffic by using deep learning. This makes it possible to combat unknown malware that cannot be dealt with using rule-based anti-virus software. By manipulating the network through programing, we can flexibly deal with malware. We propose running deep learning on a software-defined network to prevent host detection after infection and secondary damage detection of an infected host. In the proposed method, we add a connection block to the external network and perform network isolation to prevent internal infection.