Detecting DDoS Attacks in Software Defined Networks Using Deep Learning Techniques: A Survey

Ntumpha Patrick Mwanza, Jugal Kalita

Abstract:

Deep Learning (DL) is increasingly being used in Software Defined Networks (SDNs) to detect Distributed Denial of Service (DDoS) attacks because of high attack detection accuracy. This paper presents a survey on the types of deep learning techniques used to detect DDoS attacks in SDNs. Attack statistics show that DDoS attacks are on an increase. Some of the factors that have contributed to the increase in DDoS attacks is the inability of current techniques to detect unknown DDoS attacks, which can be referred to as zero-day attacks. In this work, we look at deep learning techniques and how they are used to detect DDoS attacks. The current techniques’ weaknesses are
discussed and recommendations are made.