Robust Explainable AI

The area of Explainable Artificial Intelligence (XAI) is concerned with providing methods and tools to improve the interpretability of black-box learning models. While several approaches exist to generate explanations, they are often lacking robustness, e.g., they may produce completely different explanations for similar events. This phenomenon has troubling implications, as lack of robustness indicates that explanations are not capturing the underlying decision-making process of a model an...