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

arXiv:2308.09381v2 Announce Type: replace
Abstract: 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. …

abstract access arxiv attribution become box cs.lg data data-driven decision deep learning explainability explained feature features good gradient light results type via while