English

An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS

Machine Learning 2016-05-23 v2

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

Cite

@article{arxiv.1512.07876,
  title  = {An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS},
  author = {Chao Liu and Sambuddha Ghosal and Zhanhong Jiang and Soumik Sarkar},
  journal= {arXiv preprint arXiv:1512.07876},
  year   = {2016}
}

Comments

ICCPS 2016

R2 v1 2026-06-22T12:17:43.521Z