What is it about?
Designing a system to determine network penetration using deep learning and comparing the system with machine learning algorithms using the unbalanced (UNSW-NB15) dataset. It adopted a special structure consisting of 16 layers of a one-dimensional convolutional neural network to increase the learning level of the network, as the coefficients were carefully selected to reach the required accuracy.
Featured Image
Photo by Jordan Harrison on Unsplash
Why is it important?
The experimental results showed the efficiency of the proposed system based on deep learning, as it achieved the maximum detection accuracy of 99.99% in the testing phase.
Perspectives
the findings show that the proposed 1D deep CNN architecture is more successful than conventional machine learning classifiers.
Huda Ageel
University of Mustansiriyah
Read the Original
This page is a summary of: Comparison between machine learning and deep learning for intrusion detection, January 2023, American Institute of Physics,
DOI: 10.1063/5.0119308.
You can read the full text:
Contributors
The following have contributed to this page
