Achieving 500x acceleration for adversarial robustness verification of tree-based smart grid dynamic security assessment

Abstract

This letter presents a novel and efficient adversarial robustness verification method for tree-based smart grid dynamic security assessment (DSA). Based on tree algorithms technique, the data-driven smart grid DSA has received significant research interests in recent years. However, the well-trained tree-based DSA models with high accuracy are always vulnerable caused by some physical noises or attacks, which can misclassify the DSA results. Only with the accuracy index is not enough to represent the performance of the tree-based DSA models. To provide formal robustness guarantee and select the trusted tree-based DSA models, this letter proposes an efficient adversarial robustness verification strategy with a sound robust index to quantify the ability of tree-based DSA models against any adversarial attack. Analysis results verifies the proposed strategy can achieve up to ~564X speedup.