Research on attack detection of water supply system based on deep auto-encoder

被引：0
|
作者：
Hu C. [1 ]
Zhang K. [1 ]
Quan S. [1 ]
Liu H. [1 ]
机构：
[1] School of Computer Science, China University of Geosciences (Wuhan), Wuhan
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2022年 / 50卷 / 05期
关键词：
Attack detection; Auto-encoder; Data dimension reduction; Machine learning; Water supply system;
D O I：
10.13245/j.hust.220519
中图分类号：
学科分类号：
摘要：
Considering the problem that the large-scale public facilities, especially the urban water supply system was easy to suffer from unexpected or even malicious damage due to the features of its wide coverage ration and long-term open running time in recent years, a dumbbell based deep auto-encoder (DDAE) algorithm was proposed by analyzing the sensor data of water supply system. The DDAE learned the compressed and meaningful features of input data through semi-supervised learning to achieve the purpose of dimension reduction or data generation, and the physical attack detection of water supply system could be realized by training normal samples. The effectiveness of the proposed model and algorithm was validated by simulation experiments and comprehensive performance evaluation indexes based on detection time and classification accuracy. Results show that the proposed DDAE has good detection capabilities for network physical attacks. © 2022, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：108 / 114
页数：6
相关论文
共 12 条
  • [1] NCCIC/ICS-CERT year in review: FY 2014 Rep No.14-50426, (2014)
  • [2] AGHASHAHI M, SUNDARARAJAN R, POURAHMADI M, Et al., Water distribution systems analysis symposium-battle of the attack detection algorithms (BATADAL), Proc of World Environmental and Water Resources Congress 2017, pp. 101-108, (2017)
  • [3] PASHA M F K, SOMASUNDARAM S L., An approach to detect the cyber-physical attack on water distribution system, Proc of World Environmental and Water Resources Congress 2017, pp. 703-711, (2017)
  • [4] LINA P, AMIN S., A network interdiction model for analyzing the vulnerability of water distribution systems, Proc of 3rd Int Conf on High Confidence Networked Systems, 14, pp. 135-144, (2014)
  • [5] CHANDY S E, RASEKH A, BARKER Z A, Et al., Cyber-attack detection using deep generative models with variational inference, Journal of Water Resources Planning and Management, 145, 2, (2019)
  • [6] BRENTAN B M, CAMPBELL E, LIMA G, Et al., On-line cyber-attack detection in water networks through state forecasting and control by pattern recognition, Proc of World Environmental and Water Resources Congress 2017, pp. 583-592, (2017)
  • [7] KADOSH N, FRID A, HOUSH M., Detecting cyber-physical attacks in water distribution systems: one-class classifier approach, Journal of Water Resources Planning and Management, 146, 8, (2020)
  • [8] BRENTAN B, REZENDE P, BARROS D, Et al., Cyber-attack detection in water distribution systems based on blind sources separation technique, Water, 13, 6, pp. 795-811, (2021)
  • [9] RAMOTSOELA D T, HANCKE G P, ABU-MAHFOUZ A M., Attack detection in water distribution systems using machine learning, Human-centric Computing and Information Sciences, 9, 1, pp. 1-22, (2019)
  • [10] GONZALEZ-GRANADILLO G, DIAZ R, CAUBET J, Et al., CLAP: a cross-layer analytic platform for the correlation of cyber and physical security events affecting water critical infrastructures, Journal of Cybersecurity and Privacy, 1, 2, pp. 365-386, (2021)
12