Visible to the public An Intelligent Software defined Network Controller for preventing Distributed Denial of Service Attack

TitleAn Intelligent Software defined Network Controller for preventing Distributed Denial of Service Attack
Publication TypeConference Paper
Year of Publication2018
AuthorsPrakash, A., Priyadarshini, R.
Conference Name2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT)
Date Publishedapr
KeywordsApplication Layer, attack vectors, Bayes methods, Classification algorithms, Computer architecture, Computer crime, computer network management, computer network security, cyber security, Data models, data traffic, denial of service, distributed denial of service, distributed denial of service attack, Human Behavior, infected packets, intelligent software, intelligent software defined network controller, k-nearest neighbor, machine learning algorithms, machine learning based intelligent method, naive Bayes, naive Bayes algorithm, nearest neighbour methods, network computing environment, network layer, network management mechanism, operating system, pubcrawl, Resiliency, Scalability, SDN network, Software Defined Network, Software Defined Network architecture, software defined networking, support vector machine, Support vector machines, telecommunication traffic

Software Defined Network (SDN) architecture is a new and novel way of network management mechanism. In SDN, switches do not process the incoming packets like conventional network computing environment. They match for the incoming packets in the forwarding tables and if there is none it will be sent to the controller for processing which is the operating system of the SDN. A Distributed Denial of Service (DDoS) attack is a biggest threat to cyber security in SDN network. The attack will occur at the network layer or the application layer of the compromised systems that are connected to the network. In this paper a machine learning based intelligent method is proposed which can detect the incoming packets as infected or not. The different machine learning algorithms adopted for accomplishing the task are Naive Bayes, K-Nearest neighbor (KNN) and Support vector machine (SVM) to detect the anomalous behavior of the data traffic. These three algorithms are compared according to their performances and KNN is found to be the suitable one over other two. The performance measure is taken here is the detection rate of infected packets.

Citation Keyprakash_intelligent_2018