Svm Implementation for Ddos Attacks in Software Defined Networks
Sugandhi Midha1, Gaganjot Kaur2

1Sugandhi Midha, Asst. Prof., CSE, Chandigarh University, Mohali, India.
2Gaganjot Kaur, Asst. Prof., CSE, Manav Rachna University, Faridabad, India. 

Manuscript received on September 12, 2020. | Revised Manuscript received on November 01, 2020. | Manuscript published on November 10, 2021. | PP: 205-212 | Volume-10 Issue-1, November 2020 | Retrieval Number: 100.1/ijitee.A81661110120| DOI: 10.35940/ijitee.A8166.1110120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Software Defined Network (SDN) is making software interaction with the network. SDN has made the network flexible and dynamic and also enabled the abstraction feature of applications and services. As the network is independent of any of the devices like in traditional networks there exist routers, hubs, and switches that is why it is preferable these days. Being more preferably used it has become more vulnerable in terms of security. The more common attacks that corrupt the network and hinders the efficiency are distributed denial-of-service (DDOS) attacks. DDOS is an attack that in general leads to exhaust of the network resources in turn stopping the controller. Detection of DDOS attacks requires a classification technique that provides accurate and efficient decision making. As per the analysis Support Vector Machine (SVM), the classifier technique detects more accurately and precisely the attacks. This paper produces a better approach to detecting attacks using SVM classifiers in terms of detection rate and elapsed time of the attack and it also predicts the various types of distributed denial of service attacks that have corrupted the network. 
Keywords: Software Defined Networks, Distributed Denial of service, Attacks, Support Vector Machine, classifier, Machine Learning.