Mutation-based Fault Localization of Deep Neural Networks
Mutation-based Fault Localization of Deep Neural Networks
复制标题
DOI：
10.1109/ase56229.2023.00171
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Ali Ghanbari;Deepak-George Thomas;Muhammad Arbab Arshad;Hridesh Rajan
中科院分区：
文献类型：
--
作者：
Ali Ghanbari;Deepak-George Thomas;Muhammad Arbab Arshad;Hridesh Rajan
像其他类型的软件系统一样，深度神经网络（DNN）也容易受到错误的影响。使用DNN及其在包括安全 - 关键系统在内的广泛领域的应用，保证对软件工程工具的广泛研究，以提高基于DNN的系统的可靠性。 DNN断层定位是近年来引起极大关注的一种这样的工具。本文在DNN模型的背景下重新审视了基于突变的故障定位，并提出了一种名为DeepMufl的新技术，可用于广泛的DNN模型。我们已经实施了DeepMufl，并使用了109个从Stackoverflow获得的错误评估了其有效性。我们的结果表明，DEEPMUFL通过在TOP-1位置上排名的错误层来检测53/109的错误，超过了最先进的静态和动态DNN故障定位系统，这些系统也旨在针对由BAUD的类别。 DeepMufl。此外，我们观察到，我们可以使用突变选择将预训练模型的故障定位时间减半，但仅损失了7.55％的错误位于TON-1位置的错误。
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.