Mutation-based Fault Localization of Deep Neural Networks

Thumbnail Image
Date
2023-09-10
Authors
Ghanbari, Ali
Thomas, Deepak-George
Arshad, Muhammad Arbab
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
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 top-1 position.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
preprint
Comments
This preprint is made available through arXiv at: https://doi.org/10.48550/arXiv.2309.05067. Copyright 2023, The Authors. This work is available under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/).
Rights Statement
Copyright
Funding
Subject Categories
DOI
Supplemental Resources
Collections