Small rate DDoS Violence Documentation and Protection by SDN built on Machine Learning Technique

Shibi. M. S , Suresh A.T.K. , Nisha M.D , P Ebby Darney

Application defined networking architectural framework eases the life of the network administrators by isolating the data plane from the control plane. This facilitates easy configuration of the network, provides a programmable interface for developing applications related to management, security, logging etc. and the centralized logical controller gives more control over the entire network, which has the total visibility of the network. These advantages of SDN also expose the network to the vulnerabilities and therefore the impact of the attacks are much severe in comparison to standard networks, where the network devices in itself provided protection against different attacks and limits the scope of the safety threats. During this paper, we explore various attacks which will be launched on SDN controller at different layers and secure the SDN against threats. A Distributed Denial of Service (DDoS) Violence may be a DoS Violence utilizing multiple distributed Violence sources. Increase in randomness causes decrease in vulnerabilities of system. To extenuate this threat, this paper proposes to use different techniques for the central control of SDN for various Violence detection and introduces an answer that's effective and light-weight in terms of the resources that it uses. More precisely, this project shows how DDoS attacks can exhaust controller resources and provides an answer to detect such attacks supported the variation of the destination IP address. Gridlock characteristics through statistical flow table information and uses the support vector machines (SVM) method to identify the Violence gridlock. The experiment is conducted using KDD99 dataset

Application defined networking architectural framework eases the life of the network administrators by isolating the data plane from the control plane. This facilitates easy configuration of the network, provides a programmable interface for developing applications related to management, security, logging etc. and the centralized logical controller gives more control over the entire network, which has the total visibility of the network. These advantages of SDN also expose the network to the vulnerabilities and therefore the impact of the attacks are much severe in comparison to standard networks, where the network devices in itself provided protection against different attacks and limits the scope of the safety threats. During this paper, we explore various attacks which will be launched on SDN controller at different layers and secure the SDN against threats. A Distributed Denial of Service (DDoS) Violence may be a DoS Violence utilizing multiple distributed Violence sources. Increase in randomness causes decrease in vulnerabilities of system. To extenuate this threat, this paper proposes to use different techniques for the central control of SDN for various Violence detection and introduces an answer that's effective and light-weight in terms of the resources that it uses. More precisely, this project shows how DDoS attacks can exhaust controller resources and provides an answer to detect such attacks supported the variation of the destination IP address. Gridlock characteristics through statistical flow table information and uses the support vector machines (SVM) method to identify the Violence gridlock. The experiment is conducted using KDD99 dataset

Volume 8 Issue 6, June-2023

Pages : 336 - 344