Feedback ARMA Models versus Bayesian Models towards Securing OpenFlow Controllers for SDNs

In software-defined networking (SDN), the control layers are moved away from forwarding switching layers. SDN gives more programmability and flexibility to controllers. OpenFlow is a protocol that access plane of network switch or router over network. uses centralized switches routers in environment. Security major importance for deployment. Transport layer security (TLS) used implement OpenFlow. This paper proposed new technique improve controller through modifying TLS implementation. The model referred as secured feedback using autoregressive moving average (ARMA) networks (SFBARMASDN). SFBARMASDN depended on computing incoming packets based ARMA models. Filtering techniques were filter detect malicious needed be dropped. was compared two reference One Bayesian-based other standard