一句话：提出基于类别属性违规的 DNN 图像分类器鲁棒性测试方法，用于发现混淆与偏见错误。
图像分类器已广泛用于消费、商业乃至安全攸关领域，深度神经网络（DNN）是其广泛成功的关键推动力。然而，DNN 图像分类器在敏感和关键场景下已报告多种严重错误行为，使依赖它们的软件系统面临鲁棒性风险。论文主张开发者应严格测试图像分类器，并在达到可接受标准前推迟部署。为此，作者提出一种基于类别属性违规（class property violations）的测试方法，用以检验图像分类器的鲁棒性，并针对混淆错误与偏见错误进行测试。摘要主要阐述了问题动机与方法思路，未给出具体实验设置或量化结果。
Image classifiers are an important component of today's software, from consumer and business applications to safety-critical domains. The advent of Deep Neural Networks (DNNs) is the key catalyst behind such wide-spread success. However, wide adoption comes with serious concerns about the robustness of software systems dependent on DNNs for image classification, as several severe erroneous behaviors have been reported under sensitive and critical circumstances. We argue that developers need to rigorously test their software's image classifiers and delay deployment until acceptable. We present an approach to testing image classifier robustness based on class property violations.