A Novel System to Detect Intrusions by Using SVM and Random Forest

  • K. Chandra Sekhar, P. Kavya Sri, V. Bhanu Pranathi, U. Raveena

Abstract

Intrusion detection is a new approach for providing security in networks. Enormous growth and usage of the internet focus on how to protect the data in a safe manner. The major attacks that are occurring over the network are Denial of Service (Dos),User to Root (U2R),Probe,Remote to User (R2L). Detection of these attacks has become a major challenge for researchers throughout the world. We plan to use various Machine Learning (ML) techniques for detecting intrusions. The main propaganda of this project is detecting intrusions using Support Vector Machine (SVM) and Random Forest and predicting which algorithm has the highest accuracy. As a result, paper introduces the best algorithm for detecting intrusions. We tested the performance of our proposed algorithm on the NSL-KDD intrusion detection dataset. The experiments will compare the results by using different algorithm techniques and improve accuracy of the model.

 

Keywords: Intrusion Detection, Support Vector Machine(SVM), Random Forest, NSL-KDD dataset.

Published
2020-05-30
Section
Articles