A hybrid deep learning scheme for intrusion detection in the Internet of Things

Asadullah Momand; Sana Ullah Jan; Naeem Ramzan

doi:10.1007/978-3-031-46338-9_21

A hybrid deep learning scheme for intrusion detection in the Internet of Things

Asadullah Momand, Sana Ullah Jan^*, Naeem Ramzan

^*Corresponding author for this work

School of Computing, Engineering and Physical Sciences

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

Abstract

The Internet of Things (IoT) is the connection of smart devices and objects to the internet, allowing them to share and analyze data, communicate with each other, and be controlled remotely. Several IoT devices are designed to collect, process, and store confidential data in order to perform their intended function. This information can be sensitive such as location, health, military, financial information, and biometric data. The efficient implementation of IoT networks has become increasingly reliant on security. In IoT networks, several researchers used intrusion detection systems (IDS) for the identification of cyberattacks where machine learning (ML) and deep learning (DL) are significant components. The existing IDS still needs improvements for the detection of multiclass detection to identify each category of attack separately. To improve the detection performance of IDS, this study proposes a hybrid scheme of convolutional neural networks (CNN) and gated recurrent units (GRU). The proposed hybrid scheme integrates two CNN layers and three GRU layers. The proposed scheme was assessed using the IoTID20 dataset.

Original language	English
Title of host publication	Intelligent Systems and Pattern Recognition. ISPR 2023
Place of Publication	Cham
Publisher	Springer Cham
Pages	277-287
Number of pages	11
ISBN (Electronic)	9783031463389
ISBN (Print)	9783031463372
DOIs	https://doi.org/10.1007/978-3-031-46338-9_21
Publication status	Published - 5 Nov 2023
Event	Third International Conference on Intelligent Systems and Pattern Recognition - TUI Magic Life Africana Hotel, Hammamet, Tunisia Duration: 11 May 2023 → 13 May 2023 Conference number: 3 https://ispr2023.sciencesconf.org/

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
Volume	1941
ISSN (Print)	1865-0937
ISSN (Electronic)	1865-0937

Conference

Conference	Third International Conference on Intelligent Systems and Pattern Recognition
Abbreviated title	ISPR 2023
Country/Territory	Tunisia
City	Hammamet
Period	11/05/23 → 13/05/23
Internet address	https://ispr2023.sciencesconf.org/

Keywords

convolutional neural networks
gated recurrent units
Internet of Things
intrusion detection

Access to Document

10.1007/978-3-031-46338-9_21

2023 03 30 Momand et al Intrusion acceptedAccepted author manuscript, 360 KB

Cite this

@inproceedings{db267d0954c3490b8aec63a43274e523,

title = "A hybrid deep learning scheme for intrusion detection in the Internet of Things",

abstract = "The Internet of Things (IoT) is the connection of smart devices and objects to the internet, allowing them to share and analyze data, communicate with each other, and be controlled remotely. Several IoT devices are designed to collect, process, and store confidential data in order to perform their intended function. This information can be sensitive such as location, health, military, financial information, and biometric data. The efficient implementation of IoT networks has become increasingly reliant on security. In IoT networks, several researchers used intrusion detection systems (IDS) for the identification of cyberattacks where machine learning (ML) and deep learning (DL) are significant components. The existing IDS still needs improvements for the detection of multiclass detection to identify each category of attack separately. To improve the detection performance of IDS, this study proposes a hybrid scheme of convolutional neural networks (CNN) and gated recurrent units (GRU). The proposed hybrid scheme integrates two CNN layers and three GRU layers. The proposed scheme was assessed using the IoTID20 dataset.",

keywords = "convolutional neural networks, gated recurrent units, Internet of Things, intrusion detection",

author = "Asadullah Momand and Jan, {Sana Ullah} and Naeem Ramzan",

year = "2023",

month = nov,

day = "5",

doi = "10.1007/978-3-031-46338-9_21",

language = "English",

isbn = "9783031463372",

series = "Communications in Computer and Information Science",

publisher = "Springer Cham",

pages = "277--287",

booktitle = "Intelligent Systems and Pattern Recognition. ISPR 2023",

note = "Third International Conference on Intelligent Systems and Pattern Recognition, ISPR 2023 ; Conference date: 11-05-2023 Through 13-05-2023",

url = "https://ispr2023.sciencesconf.org/",

}

Momand, A, Jan, SU & Ramzan, N 2023, A hybrid deep learning scheme for intrusion detection in the Internet of Things. in Intelligent Systems and Pattern Recognition. ISPR 2023. Communications in Computer and Information Science, vol. 1941, Springer Cham, Cham, pp. 277-287, Third International Conference on Intelligent Systems and Pattern Recognition, Hammamet, Tunisia, 11/05/23. https://doi.org/10.1007/978-3-031-46338-9_21

A hybrid deep learning scheme for intrusion detection in the Internet of Things. / Momand, Asadullah; Jan, Sana Ullah; Ramzan, Naeem.
Intelligent Systems and Pattern Recognition. ISPR 2023. Cham: Springer Cham, 2023. p. 277-287 (Communications in Computer and Information Science; Vol. 1941).

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

TY - GEN

T1 - A hybrid deep learning scheme for intrusion detection in the Internet of Things

AU - Momand, Asadullah

AU - Jan, Sana Ullah

AU - Ramzan, Naeem

N1 - Conference code: 3

PY - 2023/11/5

Y1 - 2023/11/5

N2 - The Internet of Things (IoT) is the connection of smart devices and objects to the internet, allowing them to share and analyze data, communicate with each other, and be controlled remotely. Several IoT devices are designed to collect, process, and store confidential data in order to perform their intended function. This information can be sensitive such as location, health, military, financial information, and biometric data. The efficient implementation of IoT networks has become increasingly reliant on security. In IoT networks, several researchers used intrusion detection systems (IDS) for the identification of cyberattacks where machine learning (ML) and deep learning (DL) are significant components. The existing IDS still needs improvements for the detection of multiclass detection to identify each category of attack separately. To improve the detection performance of IDS, this study proposes a hybrid scheme of convolutional neural networks (CNN) and gated recurrent units (GRU). The proposed hybrid scheme integrates two CNN layers and three GRU layers. The proposed scheme was assessed using the IoTID20 dataset.

AB - The Internet of Things (IoT) is the connection of smart devices and objects to the internet, allowing them to share and analyze data, communicate with each other, and be controlled remotely. Several IoT devices are designed to collect, process, and store confidential data in order to perform their intended function. This information can be sensitive such as location, health, military, financial information, and biometric data. The efficient implementation of IoT networks has become increasingly reliant on security. In IoT networks, several researchers used intrusion detection systems (IDS) for the identification of cyberattacks where machine learning (ML) and deep learning (DL) are significant components. The existing IDS still needs improvements for the detection of multiclass detection to identify each category of attack separately. To improve the detection performance of IDS, this study proposes a hybrid scheme of convolutional neural networks (CNN) and gated recurrent units (GRU). The proposed hybrid scheme integrates two CNN layers and three GRU layers. The proposed scheme was assessed using the IoTID20 dataset.

KW - convolutional neural networks

KW - gated recurrent units

KW - Internet of Things

KW - intrusion detection

U2 - 10.1007/978-3-031-46338-9_21

DO - 10.1007/978-3-031-46338-9_21

M3 - Conference contribution

SN - 9783031463372

T3 - Communications in Computer and Information Science

SP - 277

EP - 287

BT - Intelligent Systems and Pattern Recognition. ISPR 2023

PB - Springer Cham

CY - Cham

T2 - Third International Conference on Intelligent Systems and Pattern Recognition

Y2 - 11 May 2023 through 13 May 2023

ER -

A hybrid deep learning scheme for intrusion detection in the Internet of Things

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this