An Adaptive Framework for Attack Mitigation in SDN Environment

This paper proposes an adaptive framework for attack mitigation in Software Defined Network environments. A combined three level protection mechanism was introduced to support the functionality of secure SDN network operations. Entropy-based filtering was used to determine the legitimacy of a connection before a deep learning hybrid machine learning module made the second layer inspection. A health status verification of a specific targeted service will be deployed to confirm the current situation if an attack was in progress. A test bed has been developed to test the proposed adaptive framework and the result showed an average detection rate of 98.16%. The average false positive rate was 1.85%, which is very low considering to the size of dataset inspected. A proposed framework that covers protection for layers of SDN architecture were created and combined to ensure the secure and smooth operation of the network.