Mutants will tell: Statistical mutation-based multiple fault localization for deep learning programs

Author

• Huan XIE
• Zhengxiong DENG
• Yan LEI
• Maojin LI
• Meng YAN
• David LO, Singapore Management UniversityFollow

Publication Type

Journal Article

Publication Date

1-2026

Abstract

As deep learning (DL) systems are increasingly deployed in safety-critical domains, e.g., intelligent planning and autonomous driving, localizing faults that occur in such systems becomes indispensable. Inevitably, DL systems also suffer from faults like traditional software. Although single fault localization for DL programs has been studied, the multiple-fault localization for DL programs remains underexplored. We notice that mutation analysis is a powerful technique for locating multiple faults since it can simulate the faulty behaviors of a DL program by generating multiple mutants simultaneously. Thus, we propose MuMuFL: Statistical Mutation-based Multiple Fault Localization approach to locate the multiple faulty statements residing in a faulty DL program. The insight of MuMuFL is that the different behaviors of mutants provide valuable information for pinpointing the faulty statements of a DL fault. MuMuFL defines and leverages DL mutation operators on a DL program to simulate the faulty DL behavior. Then, MuMuFL evaluates the difference in the accuracy between the original DL model and the mutated DL model to quantify the suspiciousness of each statement being faulty. Finally, the large-scale experiments show that MuMuFL effectively localizes DL faults, e.g., localizing 36% of multiple-fault DL programs, whereas the best-performing baseline can only localize 14% of them.

Keywords

Deep learning fault; Fault localization; Mutation analysis; Probability model; Suspiciousness evaluation

Discipline

Artificial Intelligence and Robotics | Software Engineering

Research Areas

Intelligent Systems and Optimization

Publication

IEEE Transactions on Software Engineering

Volume

52

Issue

3

First Page

939

Last Page

953

ISSN

0098-5589

Identifier

10.1109/TSE.2026.3655800

Publisher

Institute of Electrical and Electronics Engineers

Citation

XIE, Huan; DENG, Zhengxiong; LEI, Yan; LI, Maojin; YAN, Meng; and LO, David. Mutants will tell: Statistical mutation-based multiple fault localization for deep learning programs. (2026). IEEE Transactions on Software Engineering. 52, (3), 939-953.
Available at: https://ink.library.smu.edu.sg/sis_research/11279

Additional URL

https://doi.org/10.1109/TSE.2026.3655800