Network Intrusion Detection: A Study on Various Learning Approaches

Sapna Sadhwani; Avani Verma; Raja Muthalagu; Pranav Mothabhau Pawar

doi:10.1109/iccike58312.2023.10131701

Network Intrusion Detection: A Study on Various Learning Approaches

Sapna Sadhwani, Avani Verma, Raja Muthalagu, Pranav Mothabhau Pawar

Birla Institute of Technology and Science Pilani

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Internet of Things (IoT) is a comprehensive paradigm where millions of devices are connected to a network. These interconnected devices create a network of intelligent systems that exchange data without the need for any computer or human communication. The devices gather data that is important to humans and businesses. Standard high-end security solutions are ineffective for safeguarding an IoT system because IoT devices have limited storage and processing capability. Due to the proliferation of innovative attacks, network security is finding it difficult to identify breaches with good accuracy. As a result, it becomes necessary to provide smart security solutions that are portable, widely dispersed, and provide long term services. The monitoring of network traffic by an intrusion detection system (IDS), which protects against prospective intrusions and preserves the network's confidentiality, integrity, and availability, is one solution. However, IDS still has difficulties detecting intrusions and improving detection accuracy while lowering false alarm rates. When dealing with heterogeneous data of varied sizes, Machine Learning (ML) and Deep Learning (DL) have already demonstrated their importance. Many modern IDS are ML based models. In this paper, ML and DL learning models like Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XG Boost (XGB), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) are used and compared. The best algorithm amongst these is compared with the existing state-of-Art models. The dataset used is UNSW-NB 15 Train set and Test set. The metrics used for comparison are Accuracy (Ac), Recall (Rc), Precision (Pr), F1 score, Mean Squared Error (MSE), training time, prediction time and total time. RF performs better than all other algorithms with Train Ac of 95.98% and Test Ac of 97.69%. It also outperforms the existing state-of-Art models achieving the highest accuracy.

Original language	English
Title of host publication	Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023
Editors	Anand Kumar, Ved Prakash Mishra, Vishal Naranje, Apurv Yadav
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	161-166
Number of pages	6
ISBN (Electronic)	9798350338263
DOIs	https://doi.org/10.1109/iccike58312.2023.10131701
State	Published - 2023
Externally published	Yes
Event	3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023 - Dubai, United Arab Emirates Duration: 9 Mar 2023 → 10 Mar 2023

Publication series

Name	Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023

Conference

Conference	3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023
Country/Territory	United Arab Emirates
City	Dubai
Period	9/03/23 → 10/03/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Binary Classification
Deep Learning
Intrusion Detection System
Machine Learning
UNSW NB-15 dataset

Access to Document

10.1109/iccike58312.2023.10131701

Cite this

Sadhwani, S., Verma, A., Muthalagu, R., & Pawar, P. M. (2023). Network Intrusion Detection: A Study on Various Learning Approaches. In A. Kumar, V. P. Mishra, V. Naranje, & A. Yadav (Eds.), Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023 (pp. 161-166). (Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/iccike58312.2023.10131701

Sadhwani, Sapna ; Verma, Avani ; Muthalagu, Raja et al. / Network Intrusion Detection : A Study on Various Learning Approaches. Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023. editor / Anand Kumar ; Ved Prakash Mishra ; Vishal Naranje ; Apurv Yadav. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 161-166 (Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023).

@inproceedings{7e096228c4304a20a9e82b11570b8702,

title = "Network Intrusion Detection: A Study on Various Learning Approaches",

abstract = "Internet of Things (IoT) is a comprehensive paradigm where millions of devices are connected to a network. These interconnected devices create a network of intelligent systems that exchange data without the need for any computer or human communication. The devices gather data that is important to humans and businesses. Standard high-end security solutions are ineffective for safeguarding an IoT system because IoT devices have limited storage and processing capability. Due to the proliferation of innovative attacks, network security is finding it difficult to identify breaches with good accuracy. As a result, it becomes necessary to provide smart security solutions that are portable, widely dispersed, and provide long term services. The monitoring of network traffic by an intrusion detection system (IDS), which protects against prospective intrusions and preserves the network's confidentiality, integrity, and availability, is one solution. However, IDS still has difficulties detecting intrusions and improving detection accuracy while lowering false alarm rates. When dealing with heterogeneous data of varied sizes, Machine Learning (ML) and Deep Learning (DL) have already demonstrated their importance. Many modern IDS are ML based models. In this paper, ML and DL learning models like Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XG Boost (XGB), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) are used and compared. The best algorithm amongst these is compared with the existing state-of-Art models. The dataset used is UNSW-NB 15 Train set and Test set. The metrics used for comparison are Accuracy (Ac), Recall (Rc), Precision (Pr), F1 score, Mean Squared Error (MSE), training time, prediction time and total time. RF performs better than all other algorithms with Train Ac of 95.98% and Test Ac of 97.69%. It also outperforms the existing state-of-Art models achieving the highest accuracy.",

keywords = "Binary Classification, Deep Learning, Intrusion Detection System, Machine Learning, UNSW NB-15 dataset",

author = "Sapna Sadhwani and Avani Verma and Raja Muthalagu and Pawar, {Pranav Mothabhau}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023 ; Conference date: 09-03-2023 Through 10-03-2023",

year = "2023",

doi = "10.1109/iccike58312.2023.10131701",

language = "אנגלית",

series = "Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "161--166",

editor = "Anand Kumar and Mishra, {Ved Prakash} and Vishal Naranje and Apurv Yadav",

booktitle = "Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023",

address = "ארצות הברית",

}

Sadhwani, S, Verma, A, Muthalagu, R & Pawar, PM 2023, Network Intrusion Detection: A Study on Various Learning Approaches. in A Kumar, VP Mishra, V Naranje & A Yadav (eds), Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023. Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023, Institute of Electrical and Electronics Engineers Inc., pp. 161-166, 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023, Dubai, United Arab Emirates, 9/03/23. https://doi.org/10.1109/iccike58312.2023.10131701

Network Intrusion Detection: A Study on Various Learning Approaches. / Sadhwani, Sapna; Verma, Avani; Muthalagu, Raja et al.
Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023. ed. / Anand Kumar; Ved Prakash Mishra; Vishal Naranje; Apurv Yadav. Institute of Electrical and Electronics Engineers Inc., 2023. p. 161-166 (Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Network Intrusion Detection

T2 - 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023

AU - Sadhwani, Sapna

AU - Verma, Avani

AU - Muthalagu, Raja

AU - Pawar, Pranav Mothabhau

PY - 2023

Y1 - 2023

N2 - Internet of Things (IoT) is a comprehensive paradigm where millions of devices are connected to a network. These interconnected devices create a network of intelligent systems that exchange data without the need for any computer or human communication. The devices gather data that is important to humans and businesses. Standard high-end security solutions are ineffective for safeguarding an IoT system because IoT devices have limited storage and processing capability. Due to the proliferation of innovative attacks, network security is finding it difficult to identify breaches with good accuracy. As a result, it becomes necessary to provide smart security solutions that are portable, widely dispersed, and provide long term services. The monitoring of network traffic by an intrusion detection system (IDS), which protects against prospective intrusions and preserves the network's confidentiality, integrity, and availability, is one solution. However, IDS still has difficulties detecting intrusions and improving detection accuracy while lowering false alarm rates. When dealing with heterogeneous data of varied sizes, Machine Learning (ML) and Deep Learning (DL) have already demonstrated their importance. Many modern IDS are ML based models. In this paper, ML and DL learning models like Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XG Boost (XGB), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) are used and compared. The best algorithm amongst these is compared with the existing state-of-Art models. The dataset used is UNSW-NB 15 Train set and Test set. The metrics used for comparison are Accuracy (Ac), Recall (Rc), Precision (Pr), F1 score, Mean Squared Error (MSE), training time, prediction time and total time. RF performs better than all other algorithms with Train Ac of 95.98% and Test Ac of 97.69%. It also outperforms the existing state-of-Art models achieving the highest accuracy.

AB - Internet of Things (IoT) is a comprehensive paradigm where millions of devices are connected to a network. These interconnected devices create a network of intelligent systems that exchange data without the need for any computer or human communication. The devices gather data that is important to humans and businesses. Standard high-end security solutions are ineffective for safeguarding an IoT system because IoT devices have limited storage and processing capability. Due to the proliferation of innovative attacks, network security is finding it difficult to identify breaches with good accuracy. As a result, it becomes necessary to provide smart security solutions that are portable, widely dispersed, and provide long term services. The monitoring of network traffic by an intrusion detection system (IDS), which protects against prospective intrusions and preserves the network's confidentiality, integrity, and availability, is one solution. However, IDS still has difficulties detecting intrusions and improving detection accuracy while lowering false alarm rates. When dealing with heterogeneous data of varied sizes, Machine Learning (ML) and Deep Learning (DL) have already demonstrated their importance. Many modern IDS are ML based models. In this paper, ML and DL learning models like Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XG Boost (XGB), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) are used and compared. The best algorithm amongst these is compared with the existing state-of-Art models. The dataset used is UNSW-NB 15 Train set and Test set. The metrics used for comparison are Accuracy (Ac), Recall (Rc), Precision (Pr), F1 score, Mean Squared Error (MSE), training time, prediction time and total time. RF performs better than all other algorithms with Train Ac of 95.98% and Test Ac of 97.69%. It also outperforms the existing state-of-Art models achieving the highest accuracy.

KW - Binary Classification

KW - Deep Learning

KW - Intrusion Detection System

KW - Machine Learning

KW - UNSW NB-15 dataset

UR - http://www.scopus.com/inward/record.url?scp=85163076150&partnerID=8YFLogxK

U2 - 10.1109/iccike58312.2023.10131701

DO - 10.1109/iccike58312.2023.10131701

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85163076150

T3 - Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023

SP - 161

EP - 166

BT - Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023

A2 - Kumar, Anand

A2 - Mishra, Ved Prakash

A2 - Naranje, Vishal

A2 - Yadav, Apurv

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 9 March 2023 through 10 March 2023

ER -

Sadhwani S, Verma A, Muthalagu R, Pawar PM. Network Intrusion Detection: A Study on Various Learning Approaches. In Kumar A, Mishra VP, Naranje V, Yadav A, editors, Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 161-166. (Proceedings of 3rd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2023). doi: 10.1109/iccike58312.2023.10131701

Network Intrusion Detection: A Study on Various Learning Approaches

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this