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
[31]   Health risk assessment of trihalomethanes in water treatment plants in Jiangsu Province, China [J].
Wang, Yumin ;
Zhu, Guangcan ;
Engel, Bernard .
ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY, 2019, 170 :346-354
[32]   Preliminary Cost Estimation Models for Construction, Operation, and Maintenance of Water Treatment Plants [J].
Sharma, Jwala R. ;
Najafi, Mohammad ;
Qasim, Syed R. .
JOURNAL OF INFRASTRUCTURE SYSTEMS, 2013, 19 (04) :451-464
[33]   POTENTIALLY TOXIC CYANOBACTERIA IN COSTA-RICAN WATER-TREATMENT PLANTS [J].
BROLATTO, MP .
REVISTA DE BIOLOGIA TROPICAL, 1994, 42 (1-2) :5-8
[34]   Trihalomethanes formation in water treatment plants and distribution lines: a monitoring and modeling scheme [J].
Azeem, S. M. Abdel ;
Burham, N. ;
Borik, M. G. ;
El Shahat, M. F. .
TOXICOLOGICAL AND ENVIRONMENTAL CHEMISTRY, 2014, 96 (01) :12-26
[36]   Evaluation of raw, treated and effluent water quality from selected water treatment plants: a case study of Lagos Water Corporation [J].
Yusuf, Kafeelah ;
Majolagbe, Abdulrafiu ;
Balogun, Sherifat .
PHYSICAL SCIENCES REVIEWS, 2021, :1319-1339
[37]   Deep Learning-Based Cyber-Physical Feature Fusion for Anomaly Detection in Industrial Control Systems [J].
Du, Yan ;
Huang, Yuanyuan ;
Wan, Guogen ;
He, Peilin .
MATHEMATICS, 2022, 10 (22)
[38]   Survey on Intrusion Detection Systems Based on Machine Learning Techniques for the Protection of Critical Infrastructure [J].
Pinto, Andrea ;
Luis-Carlos, Herrera ;
Donoso, Yezid ;
Gutierrez, Jairo A. .
SENSORS, 2023, 23 (05)
[39]   Newly engineered energy-based features for supervised anomaly detection in a physical model of a water supply system [J].
Robles-Durazno, Andres ;
Moradpoor, Naghmeh ;
McWhinnie, James ;
Russell, Gordon ;
Tan, Zhiyuan .
AD HOC NETWORKS, 2021, 120
[40]   Dataset on physicochemical and microbial properties of raw water in four drinking water treatment plants based in South Africa [J].
Masindi, Vhahangwele .
DATA IN BRIEF, 2020, 31