DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT

Mohammed M. Alani; Ernesto Damiani; Uttam Ghosh

doi:10.1109/ICDCSW56584.2022.00040

DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT

Mohammed M. Alani
, Ernesto Damiani
, Uttam Ghosh

Electrical Engineering

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

34 Scopus citations

Abstract

IoT adoption is becoming widespread in different areas of applications in our daily lives. The increased reliance on IoT devices has made them a worthy target for attackers. With malicious actors targeting water treatment facilities, power grids, and power nuclear reactors, industrial IoT poses a much higher risk in comparison to other IoT application contexts. In this pa-per, we present a deep-learning based intrusion detection system for industrial IoT. The proposed system was trained and tested using the WUSTL-IIOT-2021 dataset. Testing results showed accuracy exceeding 99% with minimally low false-positive, and false-negative rates. The proposed model was explained using SHAP values.

Original language	British English
Title of host publication	Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	169-174
Number of pages	6
ISBN (Electronic)	9781665488792
DOIs	https://doi.org/10.1109/ICDCSW56584.2022.00040
State	Published - 2022
Event	42nd IEEE International Conference on Distributed Computing Systems Workshops, ICDCSW 2022 - Bologna, Italy Duration: 10 Jul 2022 → 13 Jul 2022

Publication series

Name	Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022

Conference

Conference	42nd IEEE International Conference on Distributed Computing Systems Workshops, ICDCSW 2022
Country/Territory	Italy
City	Bologna
Period	10/07/22 → 13/07/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 6 Clean Water and Sanitation
SDG 9 Industry, Innovation, and Infrastructure

Keywords

deep learning
iiot
intrusion
intrusion detection
mlp

Access to Document

10.1109/ICDCSW56584.2022.00040

OpenUrl availability

Full text

Cite this

Alani, M. M., Damiani, E., & Ghosh, U. (2022). DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT. In Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022 (pp. 169-174). (Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDCSW56584.2022.00040

Alani, Mohammed M. ; Damiani, Ernesto ; Ghosh, Uttam. / DeepIIoT : An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT. Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 169-174 (Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022).

@inproceedings{f3b0ba1cad244d2aa352cb491951d0cd,

title = "DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT",

abstract = "IoT adoption is becoming widespread in different areas of applications in our daily lives. The increased reliance on IoT devices has made them a worthy target for attackers. With malicious actors targeting water treatment facilities, power grids, and power nuclear reactors, industrial IoT poses a much higher risk in comparison to other IoT application contexts. In this pa-per, we present a deep-learning based intrusion detection system for industrial IoT. The proposed system was trained and tested using the WUSTL-IIOT-2021 dataset. Testing results showed accuracy exceeding 99\% with minimally low false-positive, and false-negative rates. The proposed model was explained using SHAP values.",

keywords = "deep learning, iiot, intrusion, intrusion detection, mlp",

author = "Alani, \{Mohammed M.\} and Ernesto Damiani and Uttam Ghosh",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 42nd IEEE International Conference on Distributed Computing Systems Workshops, ICDCSW 2022 ; Conference date: 10-07-2022 Through 13-07-2022",

year = "2022",

doi = "10.1109/ICDCSW56584.2022.00040",

language = "British English",

series = "Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022",

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

pages = "169--174",

booktitle = "Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022",

address = "United States",

}

Alani, MM, Damiani, E & Ghosh, U 2022, DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT. in Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022. Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022, Institute of Electrical and Electronics Engineers Inc., pp. 169-174, 42nd IEEE International Conference on Distributed Computing Systems Workshops, ICDCSW 2022, Bologna, Italy, 10/07/22. https://doi.org/10.1109/ICDCSW56584.2022.00040

DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT. / Alani, Mohammed M.; Damiani, Ernesto; Ghosh, Uttam.
Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 169-174 (Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022).

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

TY - GEN

T1 - DeepIIoT

T2 - 42nd IEEE International Conference on Distributed Computing Systems Workshops, ICDCSW 2022

AU - Alani, Mohammed M.

AU - Damiani, Ernesto

AU - Ghosh, Uttam

PY - 2022

Y1 - 2022

N2 - IoT adoption is becoming widespread in different areas of applications in our daily lives. The increased reliance on IoT devices has made them a worthy target for attackers. With malicious actors targeting water treatment facilities, power grids, and power nuclear reactors, industrial IoT poses a much higher risk in comparison to other IoT application contexts. In this pa-per, we present a deep-learning based intrusion detection system for industrial IoT. The proposed system was trained and tested using the WUSTL-IIOT-2021 dataset. Testing results showed accuracy exceeding 99% with minimally low false-positive, and false-negative rates. The proposed model was explained using SHAP values.

AB - IoT adoption is becoming widespread in different areas of applications in our daily lives. The increased reliance on IoT devices has made them a worthy target for attackers. With malicious actors targeting water treatment facilities, power grids, and power nuclear reactors, industrial IoT poses a much higher risk in comparison to other IoT application contexts. In this pa-per, we present a deep-learning based intrusion detection system for industrial IoT. The proposed system was trained and tested using the WUSTL-IIOT-2021 dataset. Testing results showed accuracy exceeding 99% with minimally low false-positive, and false-negative rates. The proposed model was explained using SHAP values.

KW - deep learning

KW - iiot

KW - intrusion

KW - intrusion detection

KW - mlp

UR - https://www.scopus.com/pages/publications/85143766557

U2 - 10.1109/ICDCSW56584.2022.00040

DO - 10.1109/ICDCSW56584.2022.00040

M3 - Conference contribution

AN - SCOPUS:85143766557

T3 - Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022

SP - 169

EP - 174

BT - Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 10 July 2022 through 13 July 2022

ER -

Alani MM, Damiani E, Ghosh U. DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT. In Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 169-174. (Proceedings - 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, ICDCSW 2022). doi: 10.1109/ICDCSW56584.2022.00040

DeepIIoT: An Explainable Deep Learning Based Intrusion Detection System for Industrial IOT

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this