Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence

Bhawana  Sharma; Lokesh  Sharma; Chhagan Lal

doi:10.1007/978-981-19-6661-3_28

Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence

Bhawana Sharma, Lokesh Sharma, Chhagan Lal

Cyber Security

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

30 Downloads (Pure)

Abstract

IoT has gained immense popularity recently with advancements in technologies and big data. IoT network is dynamically increasing with the addition of devices, and the big data is generated within the network, making the network vulnerable to attacks. Thus, network security is essential, and an intrusion detection system is needed. In this paper, we proposed a deep learning-based model for detecting intrusions or attacks in IoT networks. We constructed a DNN model, applied a filter method for feature reduction, and tuned the model with different parameters. We also compared the performance of DNN with other machine learning techniques in terms of accuracy, and the proposed DNN model with weight decay of 0.0001 and dropout rate of 0.01 achieved an accuracy of 0.993, and the reduced loss on the NSL-KDD dataset having five classes. DL models are a black box and hard to understand, so we explained the model predictions using LIME.

Original language	English
Title of host publication	Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022
Editors	Sanyog Rawat, Sandeep Kumar, Pramod Kumar, Jaume Anguera
Place of Publication	Singapore
Publisher	Springer
Pages	315-324
Number of pages	10
ISBN (Electronic)	978-981-19-6661-3
ISBN (Print)	978-981-19-6660-6
DOIs	https://doi.org/10.1007/978-981-19-6661-3_28
Publication status	Published - 2023
Event	2nd International Conference on Computational Electronics for Wireless Communications, ICCWC 2022 - Mangalore, India Duration: 9 Jun 2022 → 10 Jun 2022

Publication series

Name	Lecture Notes in Networks and Systems
Volume	554
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	2nd International Conference on Computational Electronics for Wireless Communications, ICCWC 2022
Country/Territory	India
City	Mangalore
Period	9/06/22 → 10/06/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

DL
DNN
DT
Intrusion detection system (IDS)
KNN
LIME
ML
SVM

Access to Document

10.1007/978-981-19-6661-3_28

978-981-19-6661-3_28Final published version, 401 KB

Cite this

Sharma, B., Sharma, L., & Lal, C. (2023). Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence. In S. Rawat, S. Kumar, P. Kumar, & J. Anguera (Eds.), Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022 (pp. 315-324). (Lecture Notes in Networks and Systems; Vol. 554). Springer. https://doi.org/10.1007/978-981-19-6661-3_28

Sharma, Bhawana ; Sharma, Lokesh ; Lal, Chhagan. / Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation : Explainable Artificial Intelligence. Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022. editor / Sanyog Rawat ; Sandeep Kumar ; Pramod Kumar ; Jaume Anguera. Singapore : Springer, 2023. pp. 315-324 (Lecture Notes in Networks and Systems).

@inproceedings{a56315cece7b4183993777091fb28302,

title = "Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence",

abstract = "IoT has gained immense popularity recently with advancements in technologies and big data. IoT network is dynamically increasing with the addition of devices, and the big data is generated within the network, making the network vulnerable to attacks. Thus, network security is essential, and an intrusion detection system is needed. In this paper, we proposed a deep learning-based model for detecting intrusions or attacks in IoT networks. We constructed a DNN model, applied a filter method for feature reduction, and tuned the model with different parameters. We also compared the performance of DNN with other machine learning techniques in terms of accuracy, and the proposed DNN model with weight decay of 0.0001 and dropout rate of 0.01 achieved an accuracy of 0.993, and the reduced loss on the NSL-KDD dataset having five classes. DL models are a black box and hard to understand, so we explained the model predictions using LIME.",

keywords = "DL, DNN, DT, Intrusion detection system (IDS), KNN, LIME, ML, SVM",

author = "Bhawana Sharma and Lokesh Sharma and Chhagan Lal",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 2nd International Conference on Computational Electronics for Wireless Communications, ICCWC 2022 ; Conference date: 09-06-2022 Through 10-06-2022",

year = "2023",

doi = "10.1007/978-981-19-6661-3_28",

language = "English",

isbn = "978-981-19-6660-6",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "315--324",

editor = "Sanyog Rawat and Sandeep Kumar and Pramod Kumar and Jaume Anguera",

booktitle = "Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022",

}

Sharma, B, Sharma, L & Lal, C 2023, Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence. in S Rawat, S Kumar, P Kumar & J Anguera (eds), Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022. Lecture Notes in Networks and Systems, vol. 554, Springer, Singapore, pp. 315-324, 2nd International Conference on Computational Electronics for Wireless Communications, ICCWC 2022, Mangalore, India, 9/06/22. https://doi.org/10.1007/978-981-19-6661-3_28

Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence. / Sharma, Bhawana ; Sharma, Lokesh ; Lal, Chhagan.
Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022. ed. / Sanyog Rawat; Sandeep Kumar; Pramod Kumar; Jaume Anguera. Singapore: Springer, 2023. p. 315-324 (Lecture Notes in Networks and Systems; Vol. 554).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation

T2 - 2nd International Conference on Computational Electronics for Wireless Communications, ICCWC 2022

AU - Sharma, Bhawana

AU - Sharma, Lokesh

AU - Lal, Chhagan

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - IoT has gained immense popularity recently with advancements in technologies and big data. IoT network is dynamically increasing with the addition of devices, and the big data is generated within the network, making the network vulnerable to attacks. Thus, network security is essential, and an intrusion detection system is needed. In this paper, we proposed a deep learning-based model for detecting intrusions or attacks in IoT networks. We constructed a DNN model, applied a filter method for feature reduction, and tuned the model with different parameters. We also compared the performance of DNN with other machine learning techniques in terms of accuracy, and the proposed DNN model with weight decay of 0.0001 and dropout rate of 0.01 achieved an accuracy of 0.993, and the reduced loss on the NSL-KDD dataset having five classes. DL models are a black box and hard to understand, so we explained the model predictions using LIME.

AB - IoT has gained immense popularity recently with advancements in technologies and big data. IoT network is dynamically increasing with the addition of devices, and the big data is generated within the network, making the network vulnerable to attacks. Thus, network security is essential, and an intrusion detection system is needed. In this paper, we proposed a deep learning-based model for detecting intrusions or attacks in IoT networks. We constructed a DNN model, applied a filter method for feature reduction, and tuned the model with different parameters. We also compared the performance of DNN with other machine learning techniques in terms of accuracy, and the proposed DNN model with weight decay of 0.0001 and dropout rate of 0.01 achieved an accuracy of 0.993, and the reduced loss on the NSL-KDD dataset having five classes. DL models are a black box and hard to understand, so we explained the model predictions using LIME.

KW - DL

KW - DNN

KW - DT

KW - Intrusion detection system (IDS)

KW - KNN

KW - LIME

KW - ML

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85147997419&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-6661-3_28

DO - 10.1007/978-981-19-6661-3_28

M3 - Conference contribution

AN - SCOPUS:85147997419

SN - 978-981-19-6660-6

T3 - Lecture Notes in Networks and Systems

SP - 315

EP - 324

BT - Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022

A2 - Rawat, Sanyog

A2 - Kumar, Sandeep

A2 - Kumar, Pramod

A2 - Anguera, Jaume

PB - Springer

CY - Singapore

Y2 - 9 June 2022 through 10 June 2022

ER -

Sharma B, Sharma L, Lal C. Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence. In Rawat S, Kumar S, Kumar P, Anguera J, editors, Proceedings of 2nd International Conference on Computational Electronics for Wireless Communications - ICCWC 2022. Singapore: Springer. 2023. p. 315-324. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-19-6661-3_28

Anomaly-Based DNN Model for Intrusion Detection in IoT and Model Explanation: Explainable Artificial Intelligence

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this