Citation

Umair, Muhammad and Tan, Wooi Haw and Foo, Yee Loo (2024) Optimized 1D Convolutional Neural Network for Efficient Intrusion Detection in IoT Networks. In: 2024 IEEE 8th International Conference on Signal and Image Processing Applications (ICSIPA), 03-05 September 2024, Kuala Lumpur, Malaysia.

Text k.pdf - Published Version Restricted to Repository staff only Download (485kB)

Abstract

In this study, we present an optimized convolutional neural network model for classification of cyber-attacks from network traffic data, using the N-BaIoT dataset. The proposed model consists of convolutional, max pooling and dense layers. Different architectural models have been experimented with different settings such as utilizing 3,5,7,9 and 11 convolutional layers. Among these settings, the model with 5 convolutional layers outperformed the others with test accuracy of 99.91 % and an average recall, precision and F1 score of 0.99. Along with this, the proposed model has been evaluated by class wise classification report and confusion matrices. Furthermore, the model performance complexity has also been discussed and measured in GFLOPS (Giga Floating Point Operations Per Second), it shows that the proposed model with best and optimized settings achieved a value of 3.158.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Deep learning, N-BaIoT, Intrusion detection, 1D CNN.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	04 Nov 2024 02:05
Last Modified:	04 Nov 2024 02:05
URII:	http://shdl.mmu.edu.my/id/eprint/13117

Downloads

Edit (login required)