To Detect the Distributed Denial-of-Service Attacks in SDN using Machine Learning Algorithms

The reason for Software Defined Network (SDN) to gain importance in both the academics and industry as a new emerging way of network management, is its architecture which decouples the data plane (forwarding devices) and the control plane (controller) making it possible to upgrade and update into newer versions. SDN is a new or novel way of `programmable networks' which has led to growth of innovative technologies and scenarios in terms of network virtualization, flexibility, enhanced growth control, dynamic network policy, reduced operational cost. Despite, these advantages; it is also one of main reasons for cyber threats. Amongst them the most vulnerable is the DDoS attacks. DDoS attack in SDN is quite a threat to the security in SDN network. It attacks at the network layer or application layer of the infrastructure. It can cause problems as simple as inability to refresh a particular page to as severe as failure of an entire server. In this paper, DDoS is taken into consideration with SDN and proposed a IDS which studied for detection of the attackers in the real time incoming traffic. Machine Learning algorithms such as Naïve Bayes, KNN, K-Means clustering, and Linear Regression are used to form the module 1 of the IDS (the Signature IDS) and Module 2 form for uses three way handshake to identify the exact host which is an intruder. On finding the intruder it is being placed in the Access Control List (ACL). Also, analysis of efficiency of different machine learning algorithm is performed to understand the effectiveness.