Low-Power Intrusion Detection System Using SNNs 


Vol. 49,  No. 6, pp. 847-861, Jun.  2024
10.7840/kics.2024.49.6.847


PDF
  Abstract

As the number of Internet-of-Things (IoT) devices increases, our information can be easily leaked out by these devices. However, IoT devices have shown security problems due to lack of resources to use conventional security solutions. Previous studies using machine learning based on artificial neural networks propose useful security systems. However, they use lots of energy to ensure high performances and this point makes them unsuitable for IoT devices which use less energy. To address this issue, we propose a intrusion detection method using Spiking Neural Networks (SNNs). Using the proposed method, we detect malicious packets more accurately than the detection method using Deep Neural Networks (DNNs) with 15.08-40% reduction in power consumption. Furthermore, we propose the optimal network structure for the proposed method and analyze performance changes of the proposed method according to existence of a preprocessing scheme. The experimental results demonstrate SNNs-based detection method succeeds to detect malicious packets with high energy efficiency and we shows that our method can be a feasible security solution for defending IoT devices from network attacks.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Heo, H. Lee, J. Lim, "Low-Power Intrusion Detection System Using SNNs," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 6, pp. 847-861, 2024. DOI: 10.7840/kics.2024.49.6.847.

[ACM Style]

Jeong-Yun Heo, Hyun-Jong Lee, and Jae-Han Lim. 2024. Low-Power Intrusion Detection System Using SNNs. The Journal of Korean Institute of Communications and Information Sciences, 49, 6, (2024), 847-861. DOI: 10.7840/kics.2024.49.6.847.

[KICS Style]

Jeong-Yun Heo, Hyun-Jong Lee, Jae-Han Lim, "Low-Power Intrusion Detection System Using SNNs," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 6, pp. 847-861, 6. 2024. (https://doi.org/10.7840/kics.2024.49.6.847)
Vol. 49, No. 6 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880