Loading [a11y]/accessibility-menu.js
Evolving Deep Convolutional Neural Network for Intrusion Detection Based on NEAT | IEEE Conference Publication | IEEE Xplore

Evolving Deep Convolutional Neural Network for Intrusion Detection Based on NEAT


Abstract:

To defend against the malicious attacks and the unauthorized activities in Internet, intrusion detection has been widely used to ensure network security. However, with co...Show More

Abstract:

To defend against the malicious attacks and the unauthorized activities in Internet, intrusion detection has been widely used to ensure network security. However, with continuously changing attacking methods, many challenges arise since the classical detection schemes fail to detect unknown attacks intelligently. Inspired by the recent success of deep learning, it is feasible to employ convolution neural network (CNN) to accomplish the intrusion detection task. Usually the performance of a CNN depends on finding an architecture to fit the task. In this paper, we propose an automated method for exploring an optimized CNN architecture which can effectively work on intrusion detection task by extending the Neuro Evolution of Augmenting Topologies (NEAT) algorithm. Evaluation results show that the proposed method is comparable to the best human designs regarding NSL-KDD datasets of intrusion detection.
Date of Conference: 19-26 October 2020
Date Added to IEEE Xplore: 04 January 2021
ISBN Information:

ISSN Information:

Conference Location: Okayama, Japan

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.