Paper Details

In growing times, the use of internet is spreading at a lightning speed and which as a result N/Wed computerhas been increasing in our daily lives. This expanding chain of N/Wed computer weakens the servers which enablehackers to intrude on computer by using various means which may be know as well as unknown and makes them evenharder to detect. So as a protection to the computers the Intrusion Detection System (MODEL) is introduced which istrained with some MACHINE LEARNING techniques by making use of previous available data. . The used datasets werecollected during a limited period in some specific N/W and generally don't contain up-to-date data. In this paper, wepropose six machine-learning-based MODELs by using Random Forest, Gradient Boosting, Adaboost, Decision Tree,and Linear Discriminant Analysis algo. To implement a more realistic MODEL, an up-to-date security dataset, CSECIC-MODEL2018, is used instead of older and mostly worked datasets. Therefore, to increase the efficiency of thesystem depending on attack types and to decrease missed intrusions and false alarms, the imbalance ratio is reduced byusing a synthetic data generation model called Synthetic Minority Oversampling Technique. Experimental resultsdemonstrated that the proposed approach considerably increases the detection rate for rarely encountered intrusions

Prof. Pritam Ahire, Ankit Rathod, Rahul Sanap, Omkar Thora, “Increasing the Performance of MACHINE LEARNING-Based MODELs on an Imbalanced and up-to-date dataset.”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 8, Issue 12, pp. 7-10, December 2021.