Intrusion Detection System Using Deep Learning for Software Defined Networks (SDN)
Yogita Hande, Akka Lakshmi Muddana · 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT) · 2019
The new emerging area Software Defined Networking (SDN) is one of the propitious solutions to build and run the network dynamically. The distinctive architecture of Software Defined Network introduces many security challenges which demand better security mechanisms. Emerging of different and unknown types of attacks and to identify these attacks types using the anomaly detection method is a big challenging task in SDN. Intrusion Detection System (IDS) performs network traffic scanning to construct intelligence detection of promising network attacks. Many researchers proposed Machine Learning based IDS to detect the intrusion and now they are moving towards Deep Learning to achieves better accuracy. Deep Learning has a capability to provide a significant level of conceptual information through progressively consolidating basic features layer by layer into complex features. In this paper, we proposed an anomaly-based network intrusion detection system using the deep learning approach for SDN to detect different and unknown types of attacks.