Deep Learning (DL) is one of the most popular research topics in machine learning and DL-driven image recognition systems have developed rapidly. Recent research has employed metamorphic testing (MT) to detect misclassified images. Most of them discuss metamorphic relations (MR), with limited attention given to which regions should be transformed. We focus on the fact that there are sensitive regions where even small transformations can easily change the prediction results and propose an MT framework that efficiently tests for regions prone to misclassification by transforming these sensitive regions. Our evaluation demonstrated that the sensitive regions can be specified by Explainable AI (XAI) and our framework effectively detects faults.

翻译：深度学习（DL）是机器学习领域最热门的研究方向之一，基于深度学习的图像识别系统发展迅速。近年来的研究采用蜕变测试（MT）检测误分类图像，其中大部分工作关注蜕变关系（MR），而对哪些区域应进行变换的关注有限。我们注意到存在敏感区域——即使微小变换也易改变预测结果，因此提出一种MT框架，通过变换这些敏感区域来高效测试易误分类的区域。实验评估表明，可解释人工智能（XAI）能够准确识别敏感区域，且我们的框架能有效检测缺陷。