一句话：提出 deepmufl，将变异式故障定位用于 DNN，在 109 个 StackOverflow bug 上以 top-1 定位 53 个，优于现有静态与动态方法。
深度神经网络（DNN）与其他软件系统一样容易引入缺陷，而其广泛应用于安全关键领域，使得提升 DNN 可靠性的软件工程工具研究愈发重要，其中 DNN 故障定位近年来备受关注。本文在 DNN 模型背景下重新审视基于变异的故障定位（MBFL），提出了一种适用于多种 DNN 模型的新型技术 deepmufl。作者实现了该技术，并使用从 StackOverflow 收集的 109 个缺陷进行有效性评估。结果显示，deepmufl 能将 53/109 个缺陷的错误层排在 top-1 位置，优于同样针对其支持缺陷类别的当前最优静态与动态 DNN 故障定位系统。此外，作者发现通过变异选择可将预训练模型的故障定位时间减半，而 top-1 定位的缺陷仅减少 7.55%。
Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A significant uptick in using DNN, and its applications in wide-ranging areas, including safety-critical systems, warrant extensive research on software engineering tools for improving the reliability of DNN-based systems. One such tool that has gained significant attention in the recent years is DNN fault localization. This paper revisits mutation-based fault localization in the context of DNN models and proposes a novel technique, named deepmufl, applicable to a wide range of DNN models. We have implemented deepmufl and have evaluated its effectiveness using 109 bugs obtained from StackOverflow. Our results show that deepmufl detects 53/109 of the bugs by ranking the buggy layer in top-1 position, outperforming state-of-the-art static and dynamic DNN fault localization systems that are also designed to target the class of bugs supported by deepmufl. Moreover, we observed that we can halve the fault localization time for a pre-trained model using mutation selection, yet losing only 7.55% of the bugs localized in ton-1 position.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{GhanbariTAR23,
title = {Mutation-based Fault Localization of Deep Neural Networks},
author = {Ali Ghanbari and Deepak-George Thomas and Muhammad Arbab Arshad and Hridesh Rajan},
booktitle = {ASE},
year = {2023},
doi = {10.1109/ase56229.2023.00171}
}