An Unsupervised Spatiotemporal Graphical Modeling Approach to Anomaly Detection in Distributed CPS
Authors:
- Chao LiuCLChao Liu
- Sambuddha GhosalSGSambuddha Ghosal
- Zhanhong JiangZJZhanhong Jiang
- Soumik SarkarSSSoumik Sarkar
- 1 April 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Abstract
Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems. This paper presents a new data-driven framework for system-wide anomaly detection for addressing such issues. The framework is based on a spatiotemporal feature extraction scheme built on the concept of symbolic dynamics for discovering and representing causal interactions among the subsystems of a CPS. The extracted spatiotemporal features are then used to learn system-wide patterns via a Restricted Boltzmann Machine (RBM). The results show that: (1) the RBM free energy in the off-nominal conditions is different from that in the nominal conditions and can be used for anomaly detection; (2) the framework can capture multiple nominal modes with one graphical model; (3) the case studies with simulated data and an integrated building system validate the proposed approach.Keywords
This publication has 20 references indexed in Scilit:
- White House offers encouragement for cyberphysical systemsPhysics Today, 2014
- Network anomaly detection with the restricted Boltzmann machineNeurocomputing, 2013
- Symbolic Dynamic Analysis of Transient Time Series for Fault Detection in Gas Turbine EnginesJournal of Dynamic Systems, Measurement, and Control, 2012
- An Efficient Learning Procedure for Deep Boltzmann MachinesNeural Computation, 2012
- A Practical Guide to Training Restricted Boltzmann Machines2012
- Transfer entropy in magnetoencephalographic data: Quantifying information flow in cortical and cerebellar networksProgress in Biophysics and Molecular Biology, 2011
- Generalization of Hilbert transform for symbolic analysis of noisy signalsSignal Processing, 2009
- Representational Power of Restricted Boltzmann Machines and Deep Belief NetworksNeural Computation, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951