Fusing Design and Machine Learning for Anomaly Detection in Water Treatment Plants

被引:0
作者
Raman, Gauthama [1 ]
Mathur, Aditya [1 ,2 ]
机构
[1] Singapore Univ Technol & Design, Ctr Cyber Secur Res, iTrust, Singapore 487372, Singapore
[2] Purdue Univ, Dept Comp Sci, W Lafayette, IN 47907 USA
基金
新加坡国家研究基金会;
关键词
process anomaly; critical infrastructure protection; industrial control systems; Critical Infrastructure Security Showdown (CISS) 2022; fusion of design and data-centric approaches; water treatment plants;
D O I
10.3390/electronics13122267
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Accurate detection of process anomalies is crucial for maintaining reliable operations in critical infrastructures such as water treatment plants. Traditional methods for creating anomaly detection systems in these facilities typically focus on either design-based strategies, which encompass physical and engineering aspects, or on data-driven models that utilize machine learning to interpret complex data patterns. Challenges in creating these detectors arise from factors such as dynamic operating conditions, lack of design knowledge, and the complex interdependencies among heterogeneous components. This paper proposes a novel fusion detector that combines the strengths of both design-based and machine learning approaches for accurate detection of process anomalies. The proposed methodology was implemented in an operational secure water treatment (SWaT) testbed, and its performance evaluated during the Critical Infrastructure Security Showdown (CISS) 2022 event. A comparative analysis against four commercially available anomaly detection systems that participated in the CISS 2022 event revealed that our fusion detector successfully detected 19 out of 22 attacks, demonstrating high accuracy with a low rate of false positives.
引用
收藏
页数:14
相关论文
共 50 条
[41]   Drinking water treatment plant design incorporating variability and uncertainty [J].
Boccelli, Dominic L. ;
Small, Mitchell J. ;
Diwekar, Urmila M. .
JOURNAL OF ENVIRONMENTAL ENGINEERING, 2007, 133 (03) :303-312
[42]   Emergency membrane contactor based absorption system for ammonia leaks in water treatment plants [J].
Shao Jiahui ;
Fang Xuliang ;
He Yiliang ;
Jin Qiang .
JOURNAL OF ENVIRONMENTAL SCIENCES, 2008, 20 (10) :1189-1194
[44]   Coagulation process control in water treatment plants using multiple model predictive control [J].
Bello, Oladipupo ;
Hamam, Yskandar ;
Djouani, Karim .
ALEXANDRIA ENGINEERING JOURNAL, 2014, 53 (04) :939-948
[45]   Study on production wastewater in water treatment plants by Submerged micro-filtration membrane [J].
Yang, Jinman ;
Jia, Ruibao ;
Wang, Zhanjin ;
Yang, Xiaoliang ;
Pan, Zhangbin .
SUSTAINABLE DEVELOPMENT OF URBAN ENVIRONMENT AND BUILDING MATERIAL, PTS 1-4, 2012, 374-377 :982-+
[46]   Occurrence of Giardia cysts and Cryptosporidium oocysts in raw and treated water from two water treatment plants in Selangor, Malaysia [J].
Ahmad, RA ;
Lee, E ;
Tan, ITL ;
Mohamad-Kamel, AG .
WATER RESEARCH, 1997, 31 (12) :3132-3136
[47]   Machine learning for intrusion detection in industrial control systems: challenges and lessons from experimental evaluation [J].
Gauthama Raman M. R. ;
Chuadhry Mujeeb Ahmed ;
Aditya Mathur .
Cybersecurity, 4
[48]   Machine Learning-based False Data Injection Attack Detection and Localization in Power Grids [J].
Leao, Bruno P. ;
Vempati, Jagannadh ;
Muenz, Ulrich ;
Shekhar, Shashank ;
Pandey, Amit ;
Hingos, David ;
Bhela, Siddharth ;
Wang, Jing ;
Bilby, Chris .
2022 IEEE CONFERENCE ON COMMUNICATIONS AND NETWORK SECURITY (CNS), 2022,
[49]   Towards a Better Understanding of Machine Learning based Network Intrusion Detection Systems in Industrial Networks [J].
Borcherding, Anne ;
Feldmann, Lukas ;
Karch, Markus ;
Meshram, Ankush ;
Beyerer, Juergen .
PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS SECURITY AND PRIVACY (ICISSP), 2021, :314-325
[50]   Machine learning for intrusion detection in industrial control systems: challenges and lessons from experimental evaluation [J].
Raman, Gauthama M. R. ;
Ahmed, Chuadhry Mujeeb ;
Mathur, Aditya .
CYBERSECURITY, 2021, 4 (01)