Assessment of Machine Learning Algorithms for Network Intrusion Detection

Mayur Sonthalia,Jayavignesh Thyagarajan

doi:10.35940/ijeat.d8689.049420

Abstract

A Network Intrusion Detection System (NIDS) is a framework to identify network interruptions as well as abuse by checking network traffic movement and classifying it as either typical or strange. Numerous Intrusion Detection Systems have been implemented using simulated datasets like KDD’99 intrusion dataset but none of them uses a real time dataset. The proposed work performs and assesses tests to overview distinctive machine learning models reliant on KDD’99 intrusion dataset and an ongoing created dataset. The machine learning models achieved to compute required performance metrics so as to assess the chosen classifiers. The emphasis was on the accuracy metric so as to improve the recognition pace of the interruption identification framework. The actualized calculations showed that the decision tree classifier accomplished the most noteworthy estimation of accuracy while the logistic regression classifier has accomplished the least estimation of exactness for both of the datasets utilized.

Highlights

The performance metrics of the machine learning models for both the datasets reveals a similar trend in the accuracies recorded
The decision tree algorithm performs the best for all the three datasets followed by Naïve Bayes and logistic regression algorithm
In the proposed implementation and experimentation, a real time dataset was generated and the machine learning algorithms were applied on the KDD’99 intrusion dataset and the generated dataset, it is found that the decision tree algorithm performs the best as compared to Naïve Bayes and logistic regression algorithms on both the KDD’99 intrusion dataset and the real time dataset which was generated

Summary

Introduction

With the brisk headway of data innovation in the past two decades, various computer frameworks are comprehensively used by industries, businesses and various fields of the human life. Again, the fast advancement of data innovation delivered a few difficulties to construct solid systems which is an exceptionally troublesome errand. Aggressors interminably develop new undertakings and attack frameworks proposed to sidestep shields. Various attacks impact other malware or social structure to get customer affirmations that grant them access to the framework and data. A Network Intrusion Detection System (NIDS) is basic for security since it engages a framework to distinguish and respond to toxic traffic. The principle job of a network intrusion detection system is to promise IT work power is prompted when an ambush or framework interference might be happening.

Objectives

Results

Conclusion