IoT Device Fingerprinting: Machine Learning based Encrypted Traffic Analysis

Msadek, Mohamed Nizar; Soua, Ridha; Engel, Thomas

Reference : IoT Device Fingerprinting: Machine Learning based Encrypted Traffic Analysis


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Security, Reliability and Trust
	To cite this reference:	http://hdl.handle.net/10993/39318

Title :	IoT Device Fingerprinting: Machine Learning based Encrypted Traffic Analysis
Language :	English
Author, co-author :	Msadek, Mohamed Nizar [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Soua, Ridha [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Engel, Thomas [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
Publication date :	19-Apr-2019
Main document title :	The IEEE Wireless Communications and Networking Conference (WCNC)
Peer reviewed :	Yes
On invitation :	No
Audience :	International
Event name :	The IEEE Wireless Communications and Networking Conference (WCNC)
Event date :	from 15-04-2019 to 19-04-2019
Event place (city) :	Marrakech
Event country :	Morocco
Keywords :	[en] IoT Devices ; IoT network Security ; Device Type Fingerprinting ; Machine Learning ; Traffic Features
Abstract :	[en] Even in the face of strong encryption, the spectacular Internet of Things (IoT) penetration across sectors such as e-health, energy, transportation, and entertainment is expanding the attack surface, which can seriously harm users’ privacy. We demonstrate in this paper that an attacker is able to disclose sensitive information about the IoT device, such as its type,by identifying specific patterns in IoT traffic. To perform the fingerprint attack, we train machine-learning algorithms based on selected features extracted from the encrypted IoT traffic.Extensive simulations involving the baseline approach show that we achieve not only a significant mean accuracy improvement of 18.5% and but also a speedup of 18.39 times for finding the best estimators. Obtained results should spur the attention of policymakers and IoT vendors to secure the IoT devices they bring to market.
Target :	Researchers ; Professionals
Permalink :	http://hdl.handle.net/10993/39318
Framework Programme / European Project :	H2020 ; 687884 - F-Interop - FIRE+ online interoperability and performance test tools to support emerging technologies from research to standardization and market launch The standards and innovations accelerating tool

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	Fingerprinting (4).pdf		Author postprint	1.85 MB	Request a copy

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices