Learning requirements for stealth attacks
For security researchers, it provides theoretical and practical insights into data requirements for constructing stealth attacks, though the results are incremental.
The paper analyzes how training data size affects the performance of stealth attacks in state estimation, deriving an upper bound on ergodic attack performance that is shown to be tight on the IEEE 30-Bus system.
The learning data requirements are analyzed for the construction of stealth attacks in state estimation. In particular, the training data set is used to compute a sample covariance matrix that results in a random matrix with a Wishart distribution. The ergodic attack performance is defined as the average attack performance obtained by taking the expectation with respect to the distribution of the training data set. The impact of the training data size on the ergodic attack performance is characterized by proposing an upper bound for the performance. Simulations on the IEEE 30-Bus test system show that the proposed bound is tight in practical settings.