Provable Robust Saliency-based Explanations
Robust explanations of machine learning models are critical to establishing human trust in the models. The top-$k$ intersection is widely used to evaluate the robustness of explanations. However, most existing attacking and defense strategies are based on $\ell_p$ norms, thus creating a mismatch between the evaluation and optimization objectives. To this end, we define explanation thickness for measuring top-$k$ salient features ranking stability, and design the \textit{R2ET} algorithm based on a novel tractable surrogate to maximize the thickness and stabilize the top salient features efficiently. Theoretically, we prove a connection between R2ET and adversarial training; using a novel multi-objective optimization formulation and a generalization error bound, we further prove that the surrogate objective can improve both the numerical and statistical stability of the explanations. Experiments with a wide spectrum of network architectures and data modalities demonstrate that R2ET attains higher explanation robustness under stealthy attacks while retaining model accuracy.
PDF Abstract