Intrusion detection system for SDN network using deep learning approach

Software Defined Network (SDN) is considered as the main component of the next generation network. Security, in this environment, has very challenges and risks. Attacking SDN controller or injecting false flow rules could affect the network and block the entire services. To enhance the SDN network security, we propose an anomaly-based intrusion detection system using deep learning approach. This solution aims to protect the communication channel between the SDN control layer and the SDN infrastructure layer against false data injection attack, and to detect any attempt of attack in SND southbound side. We analyze the flows that circulate in the SDN network, we use the logarithm function followed by the Min/Max scalar technique to normalize the flows features. For the flow classification, we exploit the Relu and Softmax functions. We test the proposed system with CICIDS2017 dataset on an experimental platform combining Mininet environment and ONOS controller. The evaluation results demonstrate the effectiveness and efficiency of the proposed security solution.