ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis

Yair Meidan; Michael Bohadana; Asaf Shabtai; Juan David Guarnizo; Martín Ochoa; Nils Ole Tippenhauer; Yuval Elovici

doi:10.1145/3019612.3019878

ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis

Yair Meidan, Michael Bohadana, Asaf Shabtai, Juan David Guarnizo, Martín Ochoa, Nils Ole Tippenhauer, Yuval Elovici

Department of Software and Information Systems Engineering

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

345 Scopus citations

Abstract

In this work we apply machine learning algorithms on network trafic data for accurate identification of IoT devices connected to a network. To train and evaluate the classifier, we collected and labeled network trafic data from nine distinct IoT devices, and PCs and smartphones. Using supervised learning, we trained a multi-stage meta classifier; in the first stage, the classifier can distinguish between trafic generated by IoT and non-IoT devices. In the second stage, each IoT device is associated a specific IoT device class. The overall IoT classification accuracy of our model is 99.281%.

Original language	English
Title of host publication	32nd Annual ACM Symposium on Applied Computing, SAC 2017
Publisher	Association for Computing Machinery
Pages	506-509
Number of pages	4
ISBN (Electronic)	9781450344869
DOIs	https://doi.org/10.1145/3019612.3019878
State	Published - 3 Apr 2017
Event	32nd Annual ACM Symposium on Applied Computing, SAC 2017 - Marrakesh, Morocco Duration: 4 Apr 2017 → 6 Apr 2017

Publication series

Name	Proceedings of the ACM Symposium on Applied Computing
Volume	Part F128005

Conference

Conference	32nd Annual ACM Symposium on Applied Computing, SAC 2017
Country/Territory	Morocco
City	Marrakesh
Period	4/04/17 → 6/04/17

Keywords

Cyber security
Device identification
Internet of Things (IoT)
Machine learning
Network trafic analysis

ASJC Scopus subject areas

Software

Access to Document

10.1145/3019612.3019878

Cite this

Meidan, Y., Bohadana, M., Shabtai, A., Guarnizo, J. D., Ochoa, M., Tippenhauer, N. O., & Elovici, Y. (2017). ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis. In 32nd Annual ACM Symposium on Applied Computing, SAC 2017 (pp. 506-509). (Proceedings of the ACM Symposium on Applied Computing; Vol. Part F128005). Association for Computing Machinery. https://doi.org/10.1145/3019612.3019878

@inproceedings{0ffa12315ce248cbb64754778d8228af,

title = "ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis",

abstract = "In this work we apply machine learning algorithms on network trafic data for accurate identification of IoT devices connected to a network. To train and evaluate the classifier, we collected and labeled network trafic data from nine distinct IoT devices, and PCs and smartphones. Using supervised learning, we trained a multi-stage meta classifier; in the first stage, the classifier can distinguish between trafic generated by IoT and non-IoT devices. In the second stage, each IoT device is associated a specific IoT device class. The overall IoT classification accuracy of our model is 99.281%.",

keywords = "Cyber security, Device identification, Internet of Things (IoT), Machine learning, Network trafic analysis",

author = "Yair Meidan and Michael Bohadana and Asaf Shabtai and Guarnizo, {Juan David} and Mart{\'i}n Ochoa and Tippenhauer, {Nils Ole} and Yuval Elovici",

year = "2017",

month = apr,

day = "3",

doi = "10.1145/3019612.3019878",

language = "English",

series = "Proceedings of the ACM Symposium on Applied Computing",

publisher = "Association for Computing Machinery",

pages = "506--509",

booktitle = "32nd Annual ACM Symposium on Applied Computing, SAC 2017",

}

Meidan, Y, Bohadana, M, Shabtai, A, Guarnizo, JD, Ochoa, M, Tippenhauer, NO & Elovici, Y 2017, ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis. in 32nd Annual ACM Symposium on Applied Computing, SAC 2017. Proceedings of the ACM Symposium on Applied Computing, vol. Part F128005, Association for Computing Machinery, pp. 506-509, 32nd Annual ACM Symposium on Applied Computing, SAC 2017, Marrakesh, Morocco, 4/04/17. https://doi.org/10.1145/3019612.3019878

ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis. / Meidan, Yair; Bohadana, Michael; Shabtai, Asaf et al.
32nd Annual ACM Symposium on Applied Computing, SAC 2017. Association for Computing Machinery, 2017. p. 506-509 (Proceedings of the ACM Symposium on Applied Computing; Vol. Part F128005).

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

TY - GEN

T1 - ProfilIoT

T2 - 32nd Annual ACM Symposium on Applied Computing, SAC 2017

AU - Meidan, Yair

AU - Bohadana, Michael

AU - Shabtai, Asaf

AU - Guarnizo, Juan David

AU - Ochoa, Martín

AU - Tippenhauer, Nils Ole

AU - Elovici, Yuval

PY - 2017/4/3

Y1 - 2017/4/3

N2 - In this work we apply machine learning algorithms on network trafic data for accurate identification of IoT devices connected to a network. To train and evaluate the classifier, we collected and labeled network trafic data from nine distinct IoT devices, and PCs and smartphones. Using supervised learning, we trained a multi-stage meta classifier; in the first stage, the classifier can distinguish between trafic generated by IoT and non-IoT devices. In the second stage, each IoT device is associated a specific IoT device class. The overall IoT classification accuracy of our model is 99.281%.

AB - In this work we apply machine learning algorithms on network trafic data for accurate identification of IoT devices connected to a network. To train and evaluate the classifier, we collected and labeled network trafic data from nine distinct IoT devices, and PCs and smartphones. Using supervised learning, we trained a multi-stage meta classifier; in the first stage, the classifier can distinguish between trafic generated by IoT and non-IoT devices. In the second stage, each IoT device is associated a specific IoT device class. The overall IoT classification accuracy of our model is 99.281%.

KW - Cyber security

KW - Device identification

KW - Internet of Things (IoT)

KW - Machine learning

KW - Network trafic analysis

UR - http://www.scopus.com/inward/record.url?scp=85020931357&partnerID=8YFLogxK

U2 - 10.1145/3019612.3019878

DO - 10.1145/3019612.3019878

M3 - Conference contribution

AN - SCOPUS:85020931357

T3 - Proceedings of the ACM Symposium on Applied Computing

SP - 506

EP - 509

BT - 32nd Annual ACM Symposium on Applied Computing, SAC 2017

PB - Association for Computing Machinery

Y2 - 4 April 2017 through 6 April 2017

ER -

Meidan Y, Bohadana M, Shabtai A, Guarnizo JD, Ochoa M, Tippenhauer NO et al. ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis. In 32nd Annual ACM Symposium on Applied Computing, SAC 2017. Association for Computing Machinery. 2017. p. 506-509. (Proceedings of the ACM Symposium on Applied Computing). doi: 10.1145/3019612.3019878

ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this