JIITA

A Study on Comparison Analysis Between CNN and DNN for Network Anomaly Detection

JIITA, vol.4 no.1, pp.341-344, 2020
DOI: SOON

A Study on Comparison Analysis Between CNN and DNN for Network Anomaly Detection

Ahmed Al Otaibi 1), Mishaal Shah 1), Turki Alrodan 1), Donghwoon Kwon 1,*)
1) Department of Math, CSCI, and Physics, Rockford University, Rockford, IL, USA

Abstract: Network anomaly detection is a core method to prevent cyber-attacks because it monitors network traffic data to figure out whether they are normal or abnormal. A variety of research frameworks have been proposed for network anomaly detection, and nowadays deep learning-based methodologies are in the spotlight. For this reason, this research employed two deep learning models, i.e. Convolutional Neural Network (CNN) and Deep Neural Network (DNN) models, with the public dataset to examine their effectiveness for network anomaly detection. We confirmed that the CNN model outperformed the DNN model, and both models achieved 99.50% and 94.95% of the detection accuracy.

Keyword: Network anomaly detection; deep learning; CNN; DNN