Smart Lamp or Security Camera? Automatic Identification of IoT Devices

Mathias Dahl Thomsen; Alberto Giaretta; Nicola Dragoni

doi:10.1007/978-3-030-64758-2_7

Smart Lamp or Security Camera? Automatic Identification of IoT Devices

Mathias Dahl Thomsen, Alberto Giaretta^*, Nicola Dragoni

^*Corresponding author for this work

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

13 Downloads (Pure)

Abstract

The tsunami of connectivity brought by the Internet of Things is rapidly revolutionising several sectors, ranging from industry
and manufacturing, to home automation, healthcare and many more. When it comes to enforce security within an IoT network such as a smart home, there is a need to automatically recognise the type of each joining devices, in order to apply the right security policy. In this paper, we propose a method for identifying IoT devices’ types based on natural language processing (NLP), text classification, and web search engines. We implement a proof of concept and we test it against 33 different IoT devices. With a success rate of 88.9% for BACnet and 87.5% for MUD devices, our experiments show that we can efficiently and effectively identify different IoT devices.

Original language	English
Title of host publication	Proceedings of the 12^th International Networking Conference
Publisher	Springer
Publication date	2020
Pages	85-99
ISBN (Print)	978-3-030-64757-5
DOIs	https://doi.org/10.1007/978-3-030-64758-2_7
Publication status	Published - 2020
Event	12^th International Networking Conference - Virtual event, Rhodes, Greece Duration: 19 Sep 2020 → 21 Sep 2020 http://www.inc-conference.org/

Conference

Conference	12^th International Networking Conference
Location	Virtual event
Country	Greece
City	Rhodes
Period	19/09/2020 → 21/09/2020
Internet address	http://www.inc-conference.org/

Series	Lecture Notes in Networks and Systems
Volume	180
ISSN	2367-3370

Keywords

Internet of Things
Device identification
Profiling
Natural language processing
Text classification

Access to Document

10.1007/978-3-030-64758-2_7

FulltextAccepted author manuscript, 496 KB

Fingerprint Dive into the research topics of 'Smart Lamp or Security Camera? Automatic Identification of IoT Devices'. Together they form a unique fingerprint.

Cite this

@inproceedings{29884fcd6cef4063a74834897e2a2cbe,

title = "Smart Lamp or Security Camera? Automatic Identification of IoT Devices",

abstract = "The tsunami of connectivity brought by the Internet of Things is rapidly revolutionising several sectors, ranging from industryand manufacturing, to home automation, healthcare and many more. When it comes to enforce security within an IoT network such as a smart home, there is a need to automatically recognise the type of each joining devices, in order to apply the right security policy. In this paper, we propose a method for identifying IoT devices{\textquoteright} types based on natural language processing (NLP), text classification, and web search engines. We implement a proof of concept and we test it against 33 different IoT devices. With a success rate of 88.9% for BACnet and 87.5% for MUD devices, our experiments show that we can efficiently and effectively identify different IoT devices.",

keywords = "Internet of Things, Device identification, Profiling, Natural language processing, Text classification",

author = "Thomsen, {Mathias Dahl} and Alberto Giaretta and Nicola Dragoni",

year = "2020",

doi = "10.1007/978-3-030-64758-2_7",

language = "English",

isbn = "978-3-030-64757-5",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "85--99",

booktitle = "Proceedings of the 12th International Networking Conference",

note = "12<sup>th</sup> International Networking Conference, INC 2020 ; Conference date: 19-09-2020 Through 21-09-2020",

url = "http://www.inc-conference.org/",

}

Smart Lamp or Security Camera? Automatic Identification of IoT Devices. / Thomsen, Mathias Dahl; Giaretta, Alberto; Dragoni, Nicola.

Proceedings of the 12^th International Networking Conference. Springer, 2020. p. 85-99 (Lecture Notes in Networks and Systems, Vol. 180).

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

TY - GEN

T1 - Smart Lamp or Security Camera? Automatic Identification of IoT Devices

AU - Thomsen, Mathias Dahl

AU - Giaretta, Alberto

AU - Dragoni, Nicola

PY - 2020

Y1 - 2020

N2 - The tsunami of connectivity brought by the Internet of Things is rapidly revolutionising several sectors, ranging from industryand manufacturing, to home automation, healthcare and many more. When it comes to enforce security within an IoT network such as a smart home, there is a need to automatically recognise the type of each joining devices, in order to apply the right security policy. In this paper, we propose a method for identifying IoT devices’ types based on natural language processing (NLP), text classification, and web search engines. We implement a proof of concept and we test it against 33 different IoT devices. With a success rate of 88.9% for BACnet and 87.5% for MUD devices, our experiments show that we can efficiently and effectively identify different IoT devices.

AB - The tsunami of connectivity brought by the Internet of Things is rapidly revolutionising several sectors, ranging from industryand manufacturing, to home automation, healthcare and many more. When it comes to enforce security within an IoT network such as a smart home, there is a need to automatically recognise the type of each joining devices, in order to apply the right security policy. In this paper, we propose a method for identifying IoT devices’ types based on natural language processing (NLP), text classification, and web search engines. We implement a proof of concept and we test it against 33 different IoT devices. With a success rate of 88.9% for BACnet and 87.5% for MUD devices, our experiments show that we can efficiently and effectively identify different IoT devices.

KW - Internet of Things

KW - Device identification

KW - Profiling

KW - Natural language processing

KW - Text classification

U2 - 10.1007/978-3-030-64758-2_7

DO - 10.1007/978-3-030-64758-2_7

M3 - Article in proceedings

SN - 978-3-030-64757-5

T3 - Lecture Notes in Networks and Systems

SP - 85

EP - 99

BT - Proceedings of the 12th International Networking Conference

PB - Springer

T2 - 12<sup>th</sup> International Networking Conference

Y2 - 19 September 2020 through 21 September 2020

ER -