Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 17, Issue 11, Pages 7618-7627Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2021.3053304
Keywords
Security; Optimization; Training; Support vector machines; Deep learning; Automation; Analog-digital conversion; Cyber-attacks; deep belief network; ensemble learning; industrial automation and control system; population extremal optimization
Categories
Funding
- National Natural Science Foundation of China [61972288, 61972454, 61932011, 61872153, 61825203, U1736203, 61732021]
- National Key RD Plan of China [2017YFB0802203]
- Guangdong Key Laboratory of Data Security and Privacy Preserving, National Joint Engineering Research Center of Network Security Detection, and Protection Technology
Ask authors/readers for more resources
Industrial automation and control systems (IACS) heavily rely on supervisory control and data acquisition (SCADA) networks, which are vulnerable to cyber-attacks. This article introduces a population extremal optimization (PEO)-based deep belief network detection method (PEO-DBN) to detect cyber-attacks in SCADA-based IACS. Ensemble learning scheme is utilized to improve detection performance, resulting in EnPEO-DBN method. Performance analysis demonstrates the superior results of PEO-DBN and EnPEO-DBN in comparison with existing methods on real datasets from SCADA network traffic.
Industrial automation and control systems (IACS) are tremendously employing supervisory control and data acquisition (SCADA) network. However, their integration into IACS is vulnerable to various cyber-attacks. In this article, we first present population extremal optimization (PEO)-based deep belief network detection method (PEO-DBN) to detect the cyber-attacks of SCADA-based IACS. In PEO-DBN method, PEO algorithm is employed to determine the DBN's parameters, including number of hidden units and the size of mini-batch and learning rate, as there is no clear knowledge to set these parameters. Then, to enhance the performance of single method for cyber-attacks detection, the ensemble learning scheme is introduced for aggregation of the proposed PEO-DBN method, called EnPEO-DBN. The proposed detection methods are evaluated on gas pipeline system dataset and water storage tank system dataset from SCADA network traffic by comparing with some existing methods. Through performance analysis, simulation results show the superiority of PEO-DBN and EnPEO-DBN.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available