Stealth false data injection using independent component analysis in smart grid

In smart grid, the strong coupling between cyber and physical operations makes power systems vulnerable to cyber attacks. In this paper, stealth false data attacks are investigated where the attackers without prior knowledge of the power grid topology, try to make inferences through phasor observations. We show that when the system dynamics are small and can be approximated linearly, linear independent component analysis (ICA) can be applied to estimate the Jacobian matrix multiplied by the eigenvectors of the covariance matrix of the state variables. The inferred structural information can then be used to launch unobservable attacks. As demonstrated by the simulation results using data generated by MATPOWER, the proposed scheme can indeed inject false data with low detectability.