AUTHOR=Wang Weiping , Wang Chunyang , Guo Yongzhen , Yuan Manman , Luo Xiong , Gao Yang 

TITLE=Industrial Control Malicious Traffic Anomaly Detection System Based on Deep Autoencoder

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 8 - 2020

YEAR=2021

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2020.555145

DOI=10.3389/fenrg.2020.555145

ISSN=2296-598X

ABSTRACT=Industrial control network is a direct interface between information system and physical control
process. Due to the lack of authentication and encryption and other necessary security protection
design, it has became the main target of malicious attacks under the trend of increasing openness.
In order to protect the industrial control systems, we examine that the detection of abnormal traffic
in industrial control network, and propose a method of detecting abnormal traffic in industrial
control network based on Auto-Encoder technology. What’s more, a new deep Auto-Encoder
model was designed to reduce the dimensionality of traffic data in industrial control network. In
this paper, the Kullback-Leibler Divergence was added to the loss function to improve the ability
of feature extraction and the ability of recover from raw data. Finally, this model was compared
with the traditional data dimensionality reduction method (Principal Component Analysis (PCA),
Independent Component Analysis (ICA), Singular Value Decomposition (SVD)) on the gas pipline
dataset. The results show that the approach designed in this paper outperforms the three methods
in different scenes, in terms of f1score.