On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box

Understand

Attribution methods shed light on the explainability of data-driven approaches such as deep learning models by uncovering the most influential features in a to-be-explained decision.

• While determining feature attributions via gradients delivers promising results, the internal access required for acquiring gradients can be impractical under safety concerns, thus limiting the applicability of gradient-based approaches.
• In response to such limited flexibility, this paper presents \methodAbr~(gradient-estimation-based explanation), an approach that produces gradient-like explanations through only query-level access.
• The proposed approach holds a set of fundamental properties for attribution methods, which are mathematically rigorously proved, ensuring the quality of its explanations.