Mutation-based Fault Localization of Deep Neural Networks

TL;DR

This paper introduces deepmufl, a mutation-based fault localization technique for deep neural networks, demonstrating its effectiveness in identifying bugs and reducing localization time compared to existing methods.

Contribution

The paper presents deepmufl, a novel mutation-based fault localization method for DNNs, with extensive evaluation showing improved bug detection and efficiency.

Findings

deepmufl detects 53 out of 109 bugs in top-1 position

deepmufl outperforms existing fault localization systems

mutation selection halves localization time with minimal bug detection loss

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.