一句话：提出 DeepGini 测试优先级排序方法，在海量测试中优先选取更可能暴露 DNN 错误的用例以提升鲁棒性。
深度神经网络已被部署到众多软件系统中承担分类任务，但在分类效果优异的同时也会表现出错误行为，进而引发事故与损失，因此能够检测 DNN 错误行为、提升 DNN 质量的测试技术十分必要。然而自动测试中通常没有测试预言（oracle），为获得预言信息往往需要大量人工标注测试数据，显著拖慢质量保证流程。本文提出 DeepGini，一种面向海量测试用例的优先级排序方法，旨在筛选出更可能暴露错误的测试用例，从而在有限标注预算下支撑 DNN 错误检测并增强模型鲁棒性。摘要未给出具体实验设置与结果。
Deep neural networks (DNN) have been deployed in many software systems to assist in various classification tasks. In company with the fantastic effectiveness in classification, DNNs could also exhibit incorrect behaviors and result in accidents and losses. Therefore, testing techniques that can detect incorrect DNN behaviors and improve DNN quality are extremely necessary and critical. However, the testing oracle, which defines the correct output for a given input, is often not available in the automated testing. To obtain the oracle information, the testing tasks of DNN-based systems usually require expensive human efforts to label the testing data, which significantly slows down the process of quality assurance.
DOI 原文 ·
@inproceedings{paperbot6032,
title = {DeepGini: prioritizing massive tests to enhance the robustness of deep neural networks},
author = {Yang Feng and Qingkai Shi and Xinyu Gao and Jun Wan and Chunrong Fang and Zhenyu Chen},
booktitle = {ISSTA},
year = {2020},
doi = {10.1145/3395363.3397357}
}