Similarity-Based Clustering For IoT Device Classification

Guillaume Dupont; Cristoffer Leite; Daniel Ricardo dos Santos; Elisa Costante; Jerry den Hartog; Sandro Etalle

doi:10.1109/COINS51742.2021.9524201

Similarity-Based Clustering For IoT Device Classification

Guillaume Dupont, Cristoffer Leite, Daniel Ricardo dos Santos, Elisa Costante, Jerry den Hartog, Sandro Etalle

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Classifying devices connected to an enterprise network is a fundamental security control that is nevertheless challenging due to the limitations of fingerprint-based classification and black-box machine learning. In this paper, we address such limitations by proposing a similarity-based clustering method. We evaluate our solution and compare it to a state-of-the-art fingerprint-based classification engine using data from 20,000 devices. The results show that we can successfully classify around half of the unclassified devices with a high accuracy. We also validate our approach with domain experts to demonstrate its usability in producing new fingerprinting rules.

Original language	English
Title of host publication	2021 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2021
Publisher	IEEE/LEOS
Pages	1-7
Number of pages	7
ISBN (Electronic)	9781665431569
ISBN (Print)	978-1-6654-3157-6
DOIs	https://doi.org/10.1109/COINS51742.2021.9524201
Publication status	Published - 25 Aug 2021
Event	2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS) - Barcelona, Spain Duration: 23 Aug 2021 → 25 Aug 2021

Conference

Conference	2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)
Period	23/08/21 → 25/08/21

Keywords

Performance evaluation
Semantics
Process control
Machine learning
Manuals
Fingerprint recognition
Reliability engineering
Classification
Clustering
Internet of Things

Access to Document

10.1109/COINS51742.2021.9524201

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9524201

Cite this

@inproceedings{998df4dd2d9f43ad8f6529a8da1c232c,

title = "Similarity-Based Clustering For IoT Device Classification",

abstract = "Classifying devices connected to an enterprise network is a fundamental security control that is nevertheless challenging due to the limitations of fingerprint-based classification and black-box machine learning. In this paper, we address such limitations by proposing a similarity-based clustering method. We evaluate our solution and compare it to a state-of-the-art fingerprint-based classification engine using data from 20,000 devices. The results show that we can successfully classify around half of the unclassified devices with a high accuracy. We also validate our approach with domain experts to demonstrate its usability in producing new fingerprinting rules.",

keywords = "Performance evaluation, Semantics, Process control, Machine learning, Manuals, Fingerprint recognition, Reliability engineering, Classification, Clustering, Internet of Things",

author = "Guillaume Dupont and Cristoffer Leite and Santos, {Daniel Ricardo dos} and Elisa Costante and Hartog, {Jerry den} and Sandro Etalle",

year = "2021",

month = aug,

day = "25",

doi = "10.1109/COINS51742.2021.9524201",

language = "English",

isbn = "978-1-6654-3157-6",

pages = "1--7",

booktitle = "2021 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2021",

publisher = "IEEE/LEOS",

note = "2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS) ; Conference date: 23-08-2021 Through 25-08-2021",

}

Dupont, G, Leite, C, Santos, DRD, Costante, E, Hartog, JD & Etalle, S 2021, Similarity-Based Clustering For IoT Device Classification. in 2021 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2021., 9524201, IEEE/LEOS, pp. 1-7, 2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS), 23/08/21. https://doi.org/10.1109/COINS51742.2021.9524201

TY - GEN

T1 - Similarity-Based Clustering For IoT Device Classification

AU - Dupont, Guillaume

AU - Leite, Cristoffer

AU - Santos, Daniel Ricardo dos

AU - Costante, Elisa

AU - Hartog, Jerry den

AU - Etalle, Sandro

PY - 2021/8/25

Y1 - 2021/8/25

N2 - Classifying devices connected to an enterprise network is a fundamental security control that is nevertheless challenging due to the limitations of fingerprint-based classification and black-box machine learning. In this paper, we address such limitations by proposing a similarity-based clustering method. We evaluate our solution and compare it to a state-of-the-art fingerprint-based classification engine using data from 20,000 devices. The results show that we can successfully classify around half of the unclassified devices with a high accuracy. We also validate our approach with domain experts to demonstrate its usability in producing new fingerprinting rules.

AB - Classifying devices connected to an enterprise network is a fundamental security control that is nevertheless challenging due to the limitations of fingerprint-based classification and black-box machine learning. In this paper, we address such limitations by proposing a similarity-based clustering method. We evaluate our solution and compare it to a state-of-the-art fingerprint-based classification engine using data from 20,000 devices. The results show that we can successfully classify around half of the unclassified devices with a high accuracy. We also validate our approach with domain experts to demonstrate its usability in producing new fingerprinting rules.

KW - Performance evaluation

KW - Semantics

KW - Process control

KW - Machine learning

KW - Manuals

KW - Fingerprint recognition

KW - Reliability engineering

KW - Classification

KW - Clustering

KW - Internet of Things

UR - https://ieeexplore.ieee.org/document/9524201/

UR - http://www.scopus.com/inward/record.url?scp=85115381260&partnerID=8YFLogxK

U2 - 10.1109/COINS51742.2021.9524201

DO - 10.1109/COINS51742.2021.9524201

M3 - Conference contribution

SN - 978-1-6654-3157-6

SP - 1

EP - 7

BT - 2021 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2021

PB - IEEE/LEOS

T2 - 2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)

Y2 - 23 August 2021 through 25 August 2021

ER -

Similarity-Based Clustering For IoT Device Classification

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this