Title :
Intrusion detection in scada systems using one-class classification
Author :
Nader, Patric ; Honeine, Paul ; Beauseroy, Pierre
Author_Institution :
Inst. Charles Delaunay, Univ. de Technol. de Troyes, Troyes, France
Abstract :
Supervisory Control and Data Acquisition (SCADA) systems allow remote monitoring and control of critical infrastructures such as electrical power grids, gas pipelines, nuclear power plants, etc. Cyberattacks threatening these infrastructures may cause serious economic losses and may impact the health and safety of the employees and the citizens living in the area. The diversity of cyberattacks and the complexity of the studied systems make modeling cyberattacks very difficult or even impossible. This paper outlines the importance of one-class classification in detecting intrusions in SCADA systems. Two approaches are investigated, the SupportVector Data Description and the Kernel Principal Component Analysis. A case study on a gas pipeline testbed is provided with real data containing many types of cyberattacks.
Keywords :
SCADA systems; critical infrastructures; pattern classification; pipelines; principal component analysis; security of data; support vector machines; SCADA systems; critical infrastructures; cyberattack modeling; cyberattacks; economic losses; electrical power grids; employee health; employee safety; gas pipeline testbed; gas pipelines; intrusion detection; kernel principal component analysis; nuclear power plants; one-class classification; remote monitoring; supervisory control and data acquisition systems; support vector data description; Computer crime; Intrusion detection; Kernel; Pipelines; SCADA systems; Support vector machines; Training; One-class classification; SCADA systems; intrusion detection; kernel methods; novelty detection;
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2013 Proceedings of the 21st European
Conference_Location :
Marrakech
