Publication Type
Journal Article
Version
acceptedVersion
Publication Date
7-2023
Abstract
Deep learning (DL) has been applied in many applications. Meanwhile, the quality of DL systems is becoming a big concern. To evaluate the quality of DL systems, a number of DL testing techniques have been proposed. To generate test cases, a set of initial seed inputs are required. Existing testing techniques usually construct seed corpus by randomly selecting inputs from training or test dataset. Till now, there is no study on how initial seed inputs affect the performance of DL testing and how to construct an optimal one. To fill this gap, we conduct the first systematic study to evaluate the impact of seed selection strategies on DL testing. Specifically, considering three popular goals of DL testing (i.e., coverage, failure detection and robustness), we develop five seed selection strategies including three based on single-objective optimization (SOO) and two based on multi-objective optimization (MOO). We evaluate these strategies on 7 testing tools. Our results demonstrate that the selection of initial seed inputs greatly affects the testing performance. SOO-based selection can construct the best seed corpus that can boost DL testing with respect to the specific testing goal. MOO-based selection strategies construct seed corpus that achieve balanced improvement on multiple objectives.
Keywords
Deep learning testing, Seed selection, Coverage, Robustness
Discipline
OS and Networks | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
ACM Transactions on Software Engineering and Methodology
First Page
1
Last Page
33
ISSN
1049-331X
Identifier
10.1145/3607190
Publisher
Association for Computing Machinery (ACM)
Citation
ZHI, Yuhan; XIE, Xiaofei; SHEN, Chao; SUN, Jun; ZHANG, Xiaoyu; and GUAN, Xiaohong.
Seed selection for testing deep neural networks. (2023). ACM Transactions on Software Engineering and Methodology. 1-33.
Available at: https://ink.library.smu.edu.sg/sis_research/8120
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1145/3607190