A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU

Sweta Bhattacharya, Siva Ramakrishnan, Praveen Kumar Reddy M, Rajesh Kaluri, Saurabh Singh, Thippa Reddy G, Mamoun Alazab, Usman Tariq

Research output: Contribution to journalArticle

19 Downloads (Pure)

Abstract

The enormous popularity of the internet across all spheres of human life has introduced various risks of malicious attacks in the network. The activities performed over the network could be effortlessly proliferated, which has led to the emergence of intrusion detection systems. The patterns of the attacks are also dynamic, which necessitates efficient classification and prediction of cyber attacks. In this paper we propose a hybrid principal component analysis (PCA)-firefly based machine learning model to classify intrusion detection system (IDS) datasets. The dataset used in the study is collected from Kaggle. The model first performs One-Hot encoding for the transformation of the IDS datasets. The hybrid PCA-firefly algorithm is then used for dimensionality reduction. The XGBoost algorithm is implemented on the reduced dataset for classification. A comprehensive evaluation of the model is conducted with the state of the art machine learning approaches to justify the superiority of our proposed approach. The experimental results confirm the fact that the proposed model performs better than the existing machine learning models.
Original languageEnglish
Article number219
Pages (from-to)1-17
Number of pages17
JournalElectronics
Volume9
Issue number2
DOIs
Publication statusPublished - 27 Jan 2020

Fingerprint

Intrusion detection
Principal component analysis
Learning systems
Graphics processing unit
Internet

Cite this

Bhattacharya, S., Ramakrishnan, S., M, P. K. R., Kaluri, R., Singh, S., Reddy G, T., ... Tariq, U. (2020). A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU. Electronics , 9(2), 1-17. [219]. https://doi.org/10.3390/electronics9020219
Bhattacharya, Sweta ; Ramakrishnan, Siva ; M, Praveen Kumar Reddy ; Kaluri, Rajesh ; Singh, Saurabh ; Reddy G, Thippa ; Alazab, Mamoun ; Tariq, Usman. / A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU. In: Electronics . 2020 ; Vol. 9, No. 2. pp. 1-17.
@article{ae25098c44ea4653a588ded62790f68c,
title = "A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU",
abstract = "The enormous popularity of the internet across all spheres of human life has introduced various risks of malicious attacks in the network. The activities performed over the network could be effortlessly proliferated, which has led to the emergence of intrusion detection systems. The patterns of the attacks are also dynamic, which necessitates efficient classification and prediction of cyber attacks. In this paper we propose a hybrid principal component analysis (PCA)-firefly based machine learning model to classify intrusion detection system (IDS) datasets. The dataset used in the study is collected from Kaggle. The model first performs One-Hot encoding for the transformation of the IDS datasets. The hybrid PCA-firefly algorithm is then used for dimensionality reduction. The XGBoost algorithm is implemented on the reduced dataset for classification. A comprehensive evaluation of the model is conducted with the state of the art machine learning approaches to justify the superiority of our proposed approach. The experimental results confirm the fact that the proposed model performs better than the existing machine learning models.",
author = "Sweta Bhattacharya and Siva Ramakrishnan and M, {Praveen Kumar Reddy} and Rajesh Kaluri and Saurabh Singh and {Reddy G}, Thippa and Mamoun Alazab and Usman Tariq",
year = "2020",
month = "1",
day = "27",
doi = "10.3390/electronics9020219",
language = "English",
volume = "9",
pages = "1--17",
journal = "Electronics",
issn = "2079-9292",
publisher = "MDPIAG",
number = "2",

}

Bhattacharya, S, Ramakrishnan, S, M, PKR, Kaluri, R, Singh, S, Reddy G, T, Alazab, M & Tariq, U 2020, 'A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU', Electronics , vol. 9, no. 2, 219, pp. 1-17. https://doi.org/10.3390/electronics9020219

A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU. / Bhattacharya, Sweta; Ramakrishnan, Siva; M, Praveen Kumar Reddy; Kaluri, Rajesh; Singh, Saurabh; Reddy G, Thippa; Alazab, Mamoun; Tariq, Usman.

In: Electronics , Vol. 9, No. 2, 219, 27.01.2020, p. 1-17.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU

AU - Bhattacharya, Sweta

AU - Ramakrishnan, Siva

AU - M, Praveen Kumar Reddy

AU - Kaluri, Rajesh

AU - Singh, Saurabh

AU - Reddy G, Thippa

AU - Alazab, Mamoun

AU - Tariq, Usman

PY - 2020/1/27

Y1 - 2020/1/27

N2 - The enormous popularity of the internet across all spheres of human life has introduced various risks of malicious attacks in the network. The activities performed over the network could be effortlessly proliferated, which has led to the emergence of intrusion detection systems. The patterns of the attacks are also dynamic, which necessitates efficient classification and prediction of cyber attacks. In this paper we propose a hybrid principal component analysis (PCA)-firefly based machine learning model to classify intrusion detection system (IDS) datasets. The dataset used in the study is collected from Kaggle. The model first performs One-Hot encoding for the transformation of the IDS datasets. The hybrid PCA-firefly algorithm is then used for dimensionality reduction. The XGBoost algorithm is implemented on the reduced dataset for classification. A comprehensive evaluation of the model is conducted with the state of the art machine learning approaches to justify the superiority of our proposed approach. The experimental results confirm the fact that the proposed model performs better than the existing machine learning models.

AB - The enormous popularity of the internet across all spheres of human life has introduced various risks of malicious attacks in the network. The activities performed over the network could be effortlessly proliferated, which has led to the emergence of intrusion detection systems. The patterns of the attacks are also dynamic, which necessitates efficient classification and prediction of cyber attacks. In this paper we propose a hybrid principal component analysis (PCA)-firefly based machine learning model to classify intrusion detection system (IDS) datasets. The dataset used in the study is collected from Kaggle. The model first performs One-Hot encoding for the transformation of the IDS datasets. The hybrid PCA-firefly algorithm is then used for dimensionality reduction. The XGBoost algorithm is implemented on the reduced dataset for classification. A comprehensive evaluation of the model is conducted with the state of the art machine learning approaches to justify the superiority of our proposed approach. The experimental results confirm the fact that the proposed model performs better than the existing machine learning models.

U2 - 10.3390/electronics9020219

DO - 10.3390/electronics9020219

M3 - Article

VL - 9

SP - 1

EP - 17

JO - Electronics

JF - Electronics

SN - 2079-9292

IS - 2

M1 - 219

ER -

Bhattacharya S, Ramakrishnan S, M PKR, Kaluri R, Singh S, Reddy G T et al. A Novel PCA-Firefly based XGBoost classification model for Intrusion Detection in Networks using GPU. Electronics . 2020 Jan 27;9(2):1-17. 219. https://doi.org/10.3390/electronics9020219