Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning

Tony Hämmäinen; Julen Kahles

doi:10.1109/WiMob52687.2021.9606307

Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning

Tony Hämmäinen
, Julen Kahles

Department of Industrial Engineering and Management

Ericsson Finland

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

1 Citation (Scopus)

181 Downloads (Pure)

Abstract

We propose a novel machine-learning pipeline for clustering unknown IoT devices in an industrial 5G mobile-network setting. Organizing IoT devices as few homogeneous device groups improves the applicability of network-intrusion detection systems. More specifically, we develop feature engineering methods that transform IP-flows into device-level data points, define distance metrics between the data points, and apply the DBSCAN algorithm on them. Our experiments on a simulated IoT device network with varying levels of noise show that our proposed methodology outperforms alternative methods and is the only one producing a robust grouping of the IoT devices with noise present in the traffic data.

Original language	English
Title of host publication	2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	978-1-6654-2854-5
DOIs	https://doi.org/10.1109/WiMob52687.2021.9606307
Publication status	Published - 22 Nov 2021
MoE publication type	A4 Conference publication
Event	IEEE International Conference on Wireless and Mobile Computing, Networking and Communications - Bologna, Italy Duration: 11 Oct 2021 → 13 Oct 2021 Conference number: 17

Publication series

Name	IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications
Publisher	IEEE
ISSN (Electronic)	2160-4894

Workshop

Workshop	IEEE International Conference on Wireless and Mobile Computing, Networking and Communications
Abbreviated title	WiMob
Country/Territory	Italy
City	Bologna
Period	11/10/2021 → 13/10/2021

Access to Document

10.1109/WiMob52687.2021.9606307

SCI_Hammainen_Kahles_Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine LearningAccepted author manuscript, 542 KB

Cite this

Hämmäinen, T., & Kahles, J. (2021). Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning. In 2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) (IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications). IEEE. https://doi.org/10.1109/WiMob52687.2021.9606307

@inproceedings{a12908c63bc84795b00177338fef6d89,

title = "Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning",

abstract = "We propose a novel machine-learning pipeline for clustering unknown IoT devices in an industrial 5G mobile-network setting. Organizing IoT devices as few homogeneous device groups improves the applicability of network-intrusion detection systems. More specifically, we develop feature engineering methods that transform IP-flows into device-level data points, define distance metrics between the data points, and apply the DBSCAN algorithm on them. Our experiments on a simulated IoT device network with varying levels of noise show that our proposed methodology outperforms alternative methods and is the only one producing a robust grouping of the IoT devices with noise present in the traffic data.",

author = "Tony H{\"a}mm{\"a}inen and Julen Kahles",

year = "2021",

month = nov,

day = "22",

doi = "10.1109/WiMob52687.2021.9606307",

language = "English",

series = "IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications",

publisher = "IEEE",

booktitle = "2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)",

address = "United States",

note = "IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob ; Conference date: 11-10-2021 Through 13-10-2021",

}

Hämmäinen, T & Kahles, J 2021, Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning. in 2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob). IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications, IEEE, IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, Bologna, Italy, 11/10/2021. https://doi.org/10.1109/WiMob52687.2021.9606307

Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning. / Hämmäinen, Tony; Kahles, Julen.
2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob). IEEE, 2021. (IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications).

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

TY - GEN

T1 - Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning

AU - Hämmäinen, Tony

AU - Kahles, Julen

N1 - Conference code: 17

PY - 2021/11/22

Y1 - 2021/11/22

N2 - We propose a novel machine-learning pipeline for clustering unknown IoT devices in an industrial 5G mobile-network setting. Organizing IoT devices as few homogeneous device groups improves the applicability of network-intrusion detection systems. More specifically, we develop feature engineering methods that transform IP-flows into device-level data points, define distance metrics between the data points, and apply the DBSCAN algorithm on them. Our experiments on a simulated IoT device network with varying levels of noise show that our proposed methodology outperforms alternative methods and is the only one producing a robust grouping of the IoT devices with noise present in the traffic data.

AB - We propose a novel machine-learning pipeline for clustering unknown IoT devices in an industrial 5G mobile-network setting. Organizing IoT devices as few homogeneous device groups improves the applicability of network-intrusion detection systems. More specifically, we develop feature engineering methods that transform IP-flows into device-level data points, define distance metrics between the data points, and apply the DBSCAN algorithm on them. Our experiments on a simulated IoT device network with varying levels of noise show that our proposed methodology outperforms alternative methods and is the only one producing a robust grouping of the IoT devices with noise present in the traffic data.

UR - https://www.scopus.com/pages/publications/85123009612

U2 - 10.1109/WiMob52687.2021.9606307

DO - 10.1109/WiMob52687.2021.9606307

M3 - Conference article in proceedings

T3 - IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications

BT - 2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

PB - IEEE

T2 - IEEE International Conference on Wireless and Mobile Computing, Networking and Communications

Y2 - 11 October 2021 through 13 October 2021

ER -

Hämmäinen T, Kahles J. Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning. In 2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob). IEEE. 2021. (IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications). doi: 10.1109/WiMob52687.2021.9606307

Clustering Unknown IoT Devices in a 5G Mobile Network Security Context via Machine Learning

Abstract

Publication series

Workshop

Access to Document

Other files and links

Fingerprint

Cite this