Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation

Yan Naung Soe, Yaokai Feng, Paulus Insap Santosa, Rudy Hartanto, Kouichi Sakurai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The application of many IoT devices is making our world more convenient and efficient. However, it also makes a large number of cyber-attacks possible because most IoT devices have very limited resources and cannot perform ordinary intrusion detection systems. How to implement efficient and lightweight IDS in IoT environments is a critically important and challenging task. Several detection systems have been implemented on Raspberry Pi, but most of them are signature-based and only allow limited rules. In this study, a lightweight IDS based on machine learning is implemented on a Raspberry Pi. To make the system lightweight, a correlation-based feature selection algorithm is applied to significantly reduce the number of features and a lightweight classifier is utilized. The performance of our system is examined in detail and the experimental result indicates that our system is lightweight and has a much higher detection speed with almost no sacrifice of detection accuracy.

Original languageEnglish
Title of host publicationAdvanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019
EditorsMakoto Takizawa, Tomoya Enokido, Leonard Barolli, Fatos Xhafa
PublisherSpringer Verlag
Pages458-469
Number of pages12
ISBN (Print)9783030150310
DOIs
Publication statusPublished - Jan 1 2020
Event33rd International Conference on Advanced Information Networking and Applications, AINA-2019 - Matsue, Japan
Duration: Mar 27 2019Mar 29 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume926
ISSN (Print)2194-5357

Conference

Conference33rd International Conference on Advanced Information Networking and Applications, AINA-2019
CountryJapan
CityMatsue
Period3/27/193/29/19

Fingerprint

Feature extraction
Intrusion detection
Learning systems
Classifiers
Internet of things

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Soe, Y. N., Feng, Y., Santosa, P. I., Hartanto, R., & Sakurai, K. (2020). Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation. In M. Takizawa, T. Enokido, L. Barolli, & F. Xhafa (Eds.), Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019 (pp. 458-469). (Advances in Intelligent Systems and Computing; Vol. 926). Springer Verlag. https://doi.org/10.1007/978-3-030-15032-7_39

Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation. / Soe, Yan Naung; Feng, Yaokai; Santosa, Paulus Insap; Hartanto, Rudy; Sakurai, Kouichi.

Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019. ed. / Makoto Takizawa; Tomoya Enokido; Leonard Barolli; Fatos Xhafa. Springer Verlag, 2020. p. 458-469 (Advances in Intelligent Systems and Computing; Vol. 926).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Soe, YN, Feng, Y, Santosa, PI, Hartanto, R & Sakurai, K 2020, Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation. in M Takizawa, T Enokido, L Barolli & F Xhafa (eds), Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019. Advances in Intelligent Systems and Computing, vol. 926, Springer Verlag, pp. 458-469, 33rd International Conference on Advanced Information Networking and Applications, AINA-2019, Matsue, Japan, 3/27/19. https://doi.org/10.1007/978-3-030-15032-7_39
Soe YN, Feng Y, Santosa PI, Hartanto R, Sakurai K. Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation. In Takizawa M, Enokido T, Barolli L, Xhafa F, editors, Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019. Springer Verlag. 2020. p. 458-469. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-15032-7_39
Soe, Yan Naung ; Feng, Yaokai ; Santosa, Paulus Insap ; Hartanto, Rudy ; Sakurai, Kouichi. / Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation. Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019. editor / Makoto Takizawa ; Tomoya Enokido ; Leonard Barolli ; Fatos Xhafa. Springer Verlag, 2020. pp. 458-469 (Advances in Intelligent Systems and Computing).
@inproceedings{171f0fad71154174bbe837a6a9383786,
title = "Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation",
abstract = "The application of many IoT devices is making our world more convenient and efficient. However, it also makes a large number of cyber-attacks possible because most IoT devices have very limited resources and cannot perform ordinary intrusion detection systems. How to implement efficient and lightweight IDS in IoT environments is a critically important and challenging task. Several detection systems have been implemented on Raspberry Pi, but most of them are signature-based and only allow limited rules. In this study, a lightweight IDS based on machine learning is implemented on a Raspberry Pi. To make the system lightweight, a correlation-based feature selection algorithm is applied to significantly reduce the number of features and a lightweight classifier is utilized. The performance of our system is examined in detail and the experimental result indicates that our system is lightweight and has a much higher detection speed with almost no sacrifice of detection accuracy.",
author = "Soe, {Yan Naung} and Yaokai Feng and Santosa, {Paulus Insap} and Rudy Hartanto and Kouichi Sakurai",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-15032-7_39",
language = "English",
isbn = "9783030150310",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "458--469",
editor = "Makoto Takizawa and Tomoya Enokido and Leonard Barolli and Fatos Xhafa",
booktitle = "Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019",
address = "Germany",

}

TY - GEN

T1 - Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation

AU - Soe, Yan Naung

AU - Feng, Yaokai

AU - Santosa, Paulus Insap

AU - Hartanto, Rudy

AU - Sakurai, Kouichi

PY - 2020/1/1

Y1 - 2020/1/1

N2 - The application of many IoT devices is making our world more convenient and efficient. However, it also makes a large number of cyber-attacks possible because most IoT devices have very limited resources and cannot perform ordinary intrusion detection systems. How to implement efficient and lightweight IDS in IoT environments is a critically important and challenging task. Several detection systems have been implemented on Raspberry Pi, but most of them are signature-based and only allow limited rules. In this study, a lightweight IDS based on machine learning is implemented on a Raspberry Pi. To make the system lightweight, a correlation-based feature selection algorithm is applied to significantly reduce the number of features and a lightweight classifier is utilized. The performance of our system is examined in detail and the experimental result indicates that our system is lightweight and has a much higher detection speed with almost no sacrifice of detection accuracy.

AB - The application of many IoT devices is making our world more convenient and efficient. However, it also makes a large number of cyber-attacks possible because most IoT devices have very limited resources and cannot perform ordinary intrusion detection systems. How to implement efficient and lightweight IDS in IoT environments is a critically important and challenging task. Several detection systems have been implemented on Raspberry Pi, but most of them are signature-based and only allow limited rules. In this study, a lightweight IDS based on machine learning is implemented on a Raspberry Pi. To make the system lightweight, a correlation-based feature selection algorithm is applied to significantly reduce the number of features and a lightweight classifier is utilized. The performance of our system is examined in detail and the experimental result indicates that our system is lightweight and has a much higher detection speed with almost no sacrifice of detection accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85064004822&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064004822&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-15032-7_39

DO - 10.1007/978-3-030-15032-7_39

M3 - Conference contribution

AN - SCOPUS:85064004822

SN - 9783030150310

T3 - Advances in Intelligent Systems and Computing

SP - 458

EP - 469

BT - Advanced Information Networking and Applications - Proceedings of the 33rd International Conference on Advanced Information Networking and Applications AINA-2019

A2 - Takizawa, Makoto

A2 - Enokido, Tomoya

A2 - Barolli, Leonard

A2 - Xhafa, Fatos

PB - Springer Verlag

ER -