IoTDevID: A Behavior-Based Device Identification Method for the IoT

Kahraman Kostas; Mike Just; Michael Adam Lones

doi:10.1109/JIOT.2022.3191951

IoTDevID: A Behavior-Based Device Identification Method for the IoT

Kahraman Kostas, Mike Just, Michael Adam Lones

Research output: Contribution to journal › Article › peer-review

26 Citations (Scopus)

78 Downloads (Pure)

Abstract

Device identification (DI) is one way to secure a network of Internet of Things (IoT) devices, whereby devices identified as suspicious can subsequently be isolated from a network. In this study, we present a machine-learning-based method, IoTDevID, that recognizes devices through the characteristics of their network packets. As a result of using a rigorous feature analysis and selection process, our study offers a generalizable and realistic approach to modeling device behavior, achieving high predictive accuracy across two public data sets. The model's underlying feature set is shown to be more predictive than existing feature sets used for DI and is shown to generalize to data unseen during the feature selection process. Unlike most existing approaches to IoT DI, IoTDevID is able to detect devices using non-IP and low-energy protocols.

Original language	English
Pages (from-to)	23741-23749
Number of pages	9
Journal	IEEE Internet of Things Journal
Volume	9
Issue number	23
Early online date	18 Jul 2022
DOIs	https://doi.org/10.1109/JIOT.2022.3191951
Publication status	Published - 1 Dec 2022

Keywords

Fingerprinting
Internet of Things (IoT) security
machine learning

ASJC Scopus subject areas

Signal Processing
Information Systems
Hardware and Architecture
Computer Science Applications
Computer Networks and Communications

Access to Document

10.1109/JIOT.2022.3191951

Download pdf
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 927 KB

Cite this

@article{68e20da6eddf4e83a690354e47cfd653,

title = "IoTDevID: A Behavior-Based Device Identification Method for the IoT",

abstract = "Device identification (DI) is one way to secure a network of Internet of Things (IoT) devices, whereby devices identified as suspicious can subsequently be isolated from a network. In this study, we present a machine-learning-based method, IoTDevID, that recognizes devices through the characteristics of their network packets. As a result of using a rigorous feature analysis and selection process, our study offers a generalizable and realistic approach to modeling device behavior, achieving high predictive accuracy across two public data sets. The model's underlying feature set is shown to be more predictive than existing feature sets used for DI and is shown to generalize to data unseen during the feature selection process. Unlike most existing approaches to IoT DI, IoTDevID is able to detect devices using non-IP and low-energy protocols.",

keywords = "Fingerprinting, Internet of Things (IoT) security, machine learning",

author = "Kahraman Kostas and Mike Just and Lones, {Michael Adam}",

year = "2022",

month = dec,

day = "1",

doi = "10.1109/JIOT.2022.3191951",

language = "English",

volume = "9",

pages = "23741--23749",

journal = "IEEE Internet of Things Journal",

issn = "2327-4662",

publisher = "IEEE",

number = "23",

}

TY - JOUR

T1 - IoTDevID: A Behavior-Based Device Identification Method for the IoT

AU - Kostas, Kahraman

AU - Just, Mike

AU - Lones, Michael Adam

PY - 2022/12/1

Y1 - 2022/12/1

N2 - Device identification (DI) is one way to secure a network of Internet of Things (IoT) devices, whereby devices identified as suspicious can subsequently be isolated from a network. In this study, we present a machine-learning-based method, IoTDevID, that recognizes devices through the characteristics of their network packets. As a result of using a rigorous feature analysis and selection process, our study offers a generalizable and realistic approach to modeling device behavior, achieving high predictive accuracy across two public data sets. The model's underlying feature set is shown to be more predictive than existing feature sets used for DI and is shown to generalize to data unseen during the feature selection process. Unlike most existing approaches to IoT DI, IoTDevID is able to detect devices using non-IP and low-energy protocols.

AB - Device identification (DI) is one way to secure a network of Internet of Things (IoT) devices, whereby devices identified as suspicious can subsequently be isolated from a network. In this study, we present a machine-learning-based method, IoTDevID, that recognizes devices through the characteristics of their network packets. As a result of using a rigorous feature analysis and selection process, our study offers a generalizable and realistic approach to modeling device behavior, achieving high predictive accuracy across two public data sets. The model's underlying feature set is shown to be more predictive than existing feature sets used for DI and is shown to generalize to data unseen during the feature selection process. Unlike most existing approaches to IoT DI, IoTDevID is able to detect devices using non-IP and low-energy protocols.

KW - Fingerprinting

KW - Internet of Things (IoT) security

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85135225056&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2022.3191951

DO - 10.1109/JIOT.2022.3191951

M3 - Article

SN - 2327-4662

VL - 9

SP - 23741

EP - 23749

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

IS - 23

ER -

IoTDevID: A Behavior-Based Device Identification Method for the IoT

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this