ML-based Detection of Rank and Blackhole Attacks in RPL Networks

Philokypros P. Ioulianou; Vassilios G. Vassilakis; Siamak F. Shahandashti

doi:10.1109/CSNDSP54353.2022.9908049

ML-based Detection of Rank and Blackhole Attacks in RPL Networks

Philokypros P. Ioulianou, Vassilios G. Vassilakis, Siamak F. Shahandashti

Computer Science

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

Abstract

Although IoT security is a field studied extensively, recent attacks such as BotenaGo show that current security solutions cannot effectively stop the spread of IoT attacks. Machine Learning (ML) techniques are promising in improving protection against such attacks. In this work, three supervised ML algorithms are trained and evaluated for detecting rank and blackhole attacks in RPL-based IoT networks. Extensive simulations of the attacks are implemented to create a dataset and appropriate fields are identified for training the ML model. We use Google AutoML and Microsoft Azure ML platforms to train our model. Our evaluation results show that ML techniques can be effective in detecting rank and blackhole attacks, achieving a precision of 93.3%.

Original language	English
Title of host publication	13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022
Subtitle of host publication	Proceedings
Publisher	IEEE
Pages	338-343
Number of pages	6
ISBN (Electronic)	9781665410441
DOIs	https://doi.org/10.1109/CSNDSP54353.2022.9908049
Publication status	Published - 2022
Event	13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022 - Porto, Portugal Duration: 20 Jul 2022 → 22 Jul 2022

Publication series

Name	2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022

Conference

Conference	13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022
Country/Territory	Portugal
City	Porto
Period	20/07/22 → 22/07/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

RPL security
blackhole attack
rank attack
intrusion detection
Machine learning
IoT security
Internet of Things (IoT)

Access to Document

10.1109/CSNDSP54353.2022.9908049

ML_based_IDS_CSNDSP_22
This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 250 KB

Cite this

Ioulianou, P. P., Vassilakis, V. G., & Shahandashti, S. F. (2022). ML-based Detection of Rank and Blackhole Attacks in RPL Networks. In 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022: Proceedings (pp. 338-343). (2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022). IEEE. https://doi.org/10.1109/CSNDSP54353.2022.9908049

Ioulianou, Philokypros P. ; Vassilakis, Vassilios G. ; Shahandashti, Siamak F. / ML-based Detection of Rank and Blackhole Attacks in RPL Networks. 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022: Proceedings. IEEE, 2022. pp. 338-343 (2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022).

@inproceedings{63a0ee1e403847aea60db48919ddd4d1,

title = "ML-based Detection of Rank and Blackhole Attacks in RPL Networks",

abstract = "Although IoT security is a field studied extensively, recent attacks such as BotenaGo show that current security solutions cannot effectively stop the spread of IoT attacks. Machine Learning (ML) techniques are promising in improving protection against such attacks. In this work, three supervised ML algorithms are trained and evaluated for detecting rank and blackhole attacks in RPL-based IoT networks. Extensive simulations of the attacks are implemented to create a dataset and appropriate fields are identified for training the ML model. We use Google AutoML and Microsoft Azure ML platforms to train our model. Our evaluation results show that ML techniques can be effective in detecting rank and blackhole attacks, achieving a precision of 93.3%.",

keywords = "RPL security, blackhole attack, rank attack, intrusion detection, Machine learning, IoT security, Internet of Things (IoT)",

author = "Ioulianou, {Philokypros P.} and Vassilakis, {Vassilios G.} and Shahandashti, {Siamak F.}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022 ; Conference date: 20-07-2022 Through 22-07-2022",

year = "2022",

doi = "10.1109/CSNDSP54353.2022.9908049",

language = "English",

series = "2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022",

publisher = "IEEE",

pages = "338--343",

booktitle = "13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022",

address = "United States",

}

Ioulianou, PP, Vassilakis, VG & Shahandashti, SF 2022, ML-based Detection of Rank and Blackhole Attacks in RPL Networks. in 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022: Proceedings. 2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022, IEEE, pp. 338-343, 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022, Porto, Portugal, 20/07/22. https://doi.org/10.1109/CSNDSP54353.2022.9908049

ML-based Detection of Rank and Blackhole Attacks in RPL Networks. / Ioulianou, Philokypros P.; Vassilakis, Vassilios G.; Shahandashti, Siamak F.
13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022: Proceedings. IEEE, 2022. p. 338-343 (2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022).

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

TY - GEN

T1 - ML-based Detection of Rank and Blackhole Attacks in RPL Networks

AU - Ioulianou, Philokypros P.

AU - Vassilakis, Vassilios G.

AU - Shahandashti, Siamak F.

PY - 2022

Y1 - 2022

N2 - Although IoT security is a field studied extensively, recent attacks such as BotenaGo show that current security solutions cannot effectively stop the spread of IoT attacks. Machine Learning (ML) techniques are promising in improving protection against such attacks. In this work, three supervised ML algorithms are trained and evaluated for detecting rank and blackhole attacks in RPL-based IoT networks. Extensive simulations of the attacks are implemented to create a dataset and appropriate fields are identified for training the ML model. We use Google AutoML and Microsoft Azure ML platforms to train our model. Our evaluation results show that ML techniques can be effective in detecting rank and blackhole attacks, achieving a precision of 93.3%.

AB - Although IoT security is a field studied extensively, recent attacks such as BotenaGo show that current security solutions cannot effectively stop the spread of IoT attacks. Machine Learning (ML) techniques are promising in improving protection against such attacks. In this work, three supervised ML algorithms are trained and evaluated for detecting rank and blackhole attacks in RPL-based IoT networks. Extensive simulations of the attacks are implemented to create a dataset and appropriate fields are identified for training the ML model. We use Google AutoML and Microsoft Azure ML platforms to train our model. Our evaluation results show that ML techniques can be effective in detecting rank and blackhole attacks, achieving a precision of 93.3%.

KW - RPL security

KW - blackhole attack

KW - rank attack

KW - intrusion detection

KW - Machine learning

KW - IoT security

KW - Internet of Things (IoT)

UR - http://www.scopus.com/inward/record.url?scp=85140443203&partnerID=8YFLogxK

U2 - 10.1109/CSNDSP54353.2022.9908049

DO - 10.1109/CSNDSP54353.2022.9908049

M3 - Conference contribution

AN - SCOPUS:85140443203

T3 - 2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022

SP - 338

EP - 343

BT - 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022

PB - IEEE

T2 - 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022

Y2 - 20 July 2022 through 22 July 2022

ER -

Ioulianou PP, Vassilakis VG , Shahandashti SF. ML-based Detection of Rank and Blackhole Attacks in RPL Networks. In 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022: Proceedings. IEEE. 2022. p. 338-343. (2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2022). doi: 10.1109/CSNDSP54353.2022.9908049

ML-based Detection of Rank and Blackhole Attacks in RPL Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this