Anomaly Based Intrusion Detection System Using Integration of Features Selection Techniques and Random Forest Classifier

EasyChair Preprint 9934

Abstract

Today’s internets are made up of nearly half a million different networks. In any network connection, identifying the attacks by their types is a difficult task as different attacks may have various connections, and their number may vary from a few to hundreds of network connections. . To solve this problem, IDS-based on machine learning (ML) has been developed to monitor and analyze data packets to detect abnormal behaviors and new attacks. The datasets used for this anomaly based intruder detection famous data set NSLKDD[5]. It contains a large number of features and computational time is more. The more computational time leads to decay the accuracy of model, the reason behind is curse of dimensionality and Imbalance of data so handle these issues i. Feature selection algorithm[3] to reduce the dimensionality of features and include in the model, which produce better results and require less computation time than using all of the features. ii. Imbalance of data is handle by adjust over fitting and under fitting of data. In this paper, we developed a system that combines feature selection Techniques and Random Forest model as a classifier. The NSL-KDD dataset[4] used to validate our system. We have compared with existing algorithms and found that our proposed model outperformed the others in terms of accuracy, recall, precision, F-measure, and false-alarm rate.

Keyphrases: Feature selection method, NSL-KDD, Random Forest

@booklet{EasyChair:9934,
  author    = {A Srinivas and K Sagar},
  title     = {Anomaly Based Intrusion Detection System Using Integration of Features Selection Techniques and Random Forest Classifier},
  howpublished = {EasyChair Preprint 9934},
  year      = {EasyChair, 2023}}