Intrusion Detection System in Software Defined Networks using Machine Learning Approach

Jayasri P, Atchaya A, Sanfeeya Parveen M, Ramprasath J

Naïve Bayes, k-means clustering, Weka, SDN, KDD cupp99

Now a days, Network Security is becoming the most challenging task. As a result in the growth of internet, the attacks in the network has also been increased. This can be hold back by the intrusion detection system, it identifies the unwanted attacks and unauthorized access in the network. The comprehensive overview of the detailed survey is analyzed with the existing dataset for identifying the unusual attacks in the network. Here machine learning classification algorithms is used to detect several category of attacks. The machine learning techniques can result in higher detection rates, lower false alarm rates and reasonable computation and communication costs. In this paper KDD cup99 is used to evaluate the machine learning algorithms for intrusion detection system. Here we have implemented the experiment on intrusion detection system which uses machine learning algorithms like Naïve Bayes and k-means clustering algorithm.

Received: 08 Jan 2021; Received in revised form: 25 Feb 2021; Accepted: 18 Mar 2021; Available online: 16 Apr 2021

10.22161/ijaers.84.16