Network Intrusion Detection Using CatBoost Algorithm
Vinay Jain
Intrusion Detection, NSL-KDD Dataset, Boosting, CatBoost algorithm, Classification, Accuracy, False Positive Rate, Detection Rate
With the rapid advancement in technology, the usage of devices generating digital data has surged and thus, resulted in increased network traffic. This has also raised the issues of network security commensurately as increased network traffic means increased vulnerability of data to hackers. Due to these reasons, intrusion detection system has been an important research issue. An intrusion detection system is like a defense mechanism that prevents unauthorized access to the data or network of an organization. Boosting algorithms are ensemble techniques which form a strong model from weak ones by taking into account the previous classifiers success. In this paper, an intrusion detection system is proposed using a boosting technique called CatBoost algorithm. A binary classification i.e., differentiating benign and malignant intrusions, and a multi-class classification i.e., identifying intrusions as benign or an attack type of the category DoS, Probe, U2R and R2L, is performed using CatBoost algorithm. Later the results from both types of classifications are analyzed to see the algorithm’s efficiency in different detection scenarios.
Article Details
Unique Paper ID: 148286

Publication Volume & Issue: Volume 6, Issue 1

Page(s): 228 - 232
Article Preview & Download

Share This Article

Conference Alert


International conference on Management, Science, Technology, Engineering, Pharmact and Humanities.

Latest Publication

Go To Issue

Call For Paper

Volume 7 Issue 9

Last Date 25 February 2020

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews

Contact Details