AuDI: Towards Autonomous IoT Device-Type Identification using Periodic Communication

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Standard

AuDI : Towards Autonomous IoT Device-Type Identification using Periodic Communication. / Marchal, Samuel; Miettinen, Markus; Nguyen, Thien Duc; Sadeghi, Ahmad-Reza; Asokan, N.

julkaisussa: IEEE Journal on Selected Areas in Communications, Vuosikerta 37, Nro 6, 8664655, 06.2019, s. 1402-1412.

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Harvard

APA

Vancouver

Author

Marchal, Samuel ; Miettinen, Markus ; Nguyen, Thien Duc ; Sadeghi, Ahmad-Reza ; Asokan, N. / AuDI : Towards Autonomous IoT Device-Type Identification using Periodic Communication. Julkaisussa: IEEE Journal on Selected Areas in Communications. 2019 ; Vuosikerta 37, Nro 6. Sivut 1402-1412.

Bibtex - Lataa

@article{4aa54e18407e4086bb6fb0141c536d3c,
title = "AuDI: Towards Autonomous IoT Device-Type Identification using Periodic Communication",
abstract = "IoT devices are being widely deployed. But the huge variance among them in the level of security and requirements for network resources makes it infeasible to manage IoT networks using a common generic policy. One solution to this challenge is to define policies for classes of devices based on device type. In this paper, we present AUDI, a system for quickly and effectively identifying the type of a device in an IoT network by analyzing their network communications. AuDI models the periodic communication traffic of IoT devices using an unsupervised learning method to perform identification. In contrast to prior work, AuDI operates autonomously after initial setup, learning, without human intervention nor labeled data, to identify previously unseen device types. AuDI can identify the type of a device in any mode of operation or stage of lifecycle of the device. Via systematic experiments using 33 off-the-shelf IoT devices, we show that AuDI is effective (98.2{\%} accuracy).",
keywords = "Internet of Things, device-type identification, autonomous IoT device identification, self-learning",
author = "Samuel Marchal and Markus Miettinen and Nguyen, {Thien Duc} and Ahmad-Reza Sadeghi and N. Asokan",
year = "2019",
month = "6",
doi = "10.1109/JSAC.2019.2904364",
language = "English",
volume = "37",
pages = "1402--1412",
journal = "IEEE Journal on Selected Areas in Communications",
issn = "0733-8716",
number = "6",

}

RIS - Lataa

TY - JOUR

T1 - AuDI

T2 - Towards Autonomous IoT Device-Type Identification using Periodic Communication

AU - Marchal, Samuel

AU - Miettinen, Markus

AU - Nguyen, Thien Duc

AU - Sadeghi, Ahmad-Reza

AU - Asokan, N.

PY - 2019/6

Y1 - 2019/6

N2 - IoT devices are being widely deployed. But the huge variance among them in the level of security and requirements for network resources makes it infeasible to manage IoT networks using a common generic policy. One solution to this challenge is to define policies for classes of devices based on device type. In this paper, we present AUDI, a system for quickly and effectively identifying the type of a device in an IoT network by analyzing their network communications. AuDI models the periodic communication traffic of IoT devices using an unsupervised learning method to perform identification. In contrast to prior work, AuDI operates autonomously after initial setup, learning, without human intervention nor labeled data, to identify previously unseen device types. AuDI can identify the type of a device in any mode of operation or stage of lifecycle of the device. Via systematic experiments using 33 off-the-shelf IoT devices, we show that AuDI is effective (98.2% accuracy).

AB - IoT devices are being widely deployed. But the huge variance among them in the level of security and requirements for network resources makes it infeasible to manage IoT networks using a common generic policy. One solution to this challenge is to define policies for classes of devices based on device type. In this paper, we present AUDI, a system for quickly and effectively identifying the type of a device in an IoT network by analyzing their network communications. AuDI models the periodic communication traffic of IoT devices using an unsupervised learning method to perform identification. In contrast to prior work, AuDI operates autonomously after initial setup, learning, without human intervention nor labeled data, to identify previously unseen device types. AuDI can identify the type of a device in any mode of operation or stage of lifecycle of the device. Via systematic experiments using 33 off-the-shelf IoT devices, we show that AuDI is effective (98.2% accuracy).

KW - Internet of Things

KW - device-type identification

KW - autonomous IoT device identification

KW - self-learning

UR - http://www.scopus.com/inward/record.url?scp=85065882414&partnerID=8YFLogxK

U2 - 10.1109/JSAC.2019.2904364

DO - 10.1109/JSAC.2019.2904364

M3 - Article

VL - 37

SP - 1402

EP - 1412

JO - IEEE Journal on Selected Areas in Communications

JF - IEEE Journal on Selected Areas in Communications

SN - 0733-8716

IS - 6

M1 - 8664655

ER -

ID: 32144500