一句话：用生成式模型产生高层特征变化的测试输入，发现其他DNN测试方法无法检测的故障。
现有深度神经网络（DNN）测试方法通过约束原始特征（如图像像素值）与已知标签的样本保持很小距离来回避 oracle 问题，但这限制了可检测故障的种类。本文提出一种新的 DNN 测试方法，其核心是借助生成式机器学习生成全新的测试输入：这些输入在高层特征上发生变化（对图像而言包括物体形状、位置、纹理和颜色），同时保持标签语义。作者在人为注入故障以及当前最先进的 DNN 模型上进行了评估，证明该方法既能检出刻意注入的故障，也能发现模型中的新故障；而在这两种情况下，既有测试方法均无法找到这些故障。该工作表明，通过生成式模型探索高层语义特征空间，可以显著扩展 DNN 测试的故障检测能力。
Existing methods for testing DNNs solve the oracle problem by constraining the raw features (e.g. image pixel values) to be within a small distance of a dataset example for which the desired DNN output is known. But this limits the kinds of faults these approaches are able to detect. In this paper, we introduce a novel DNN testing method that is able to find faults in DNNs that other methods cannot. The crux is that, by leveraging generative machine learning, we can generate fresh test inputs that vary in their high-level features (for images, these include object shape, location, texture, and colour). We demonstrate that our approach is capable of detecting deliberately injected faults as well as new faults in state-of-the-art DNNs, and that in both cases, existing methods are unable to find these faults.