SparseTG-GS: Test Case Generation via Sparse Perturbation Group

Deep Neural Networks (DNNs) have been widely applied in the field of computer vision. While DNNs exhibit remarkable accuracy in classification tasks, they remain susceptible to adversarial examples. Robustness testing for DNNs has become crucial. Existing test case generation methods suffer from certain limitations, such as dispersed distribution of perturbations, insufficient realism, and high time cost. This article proposes a test case generation method, Sparse Perturbation-Based Test Case Generation—Group-Wise Sparsity (SparseTG-GS). Initially, superpixel segmentation is applied to partition the input image into multiple superpixels. Next, perturbation groups are iteratively introduced into the superpixels until the perturbed image effectively compromises the target DNN. Finally, based on the importance of each perturbation, the initial perturbation scheme is improved by re-adding perturbation groups and minimizing superfluous perturbations and perturbation magnitudes. We improve the AdvGAN framework to construct the Generative Adversarial Networks (GANs) for calculating a perturbation importance matrix for test cases with enhanced optimization efficiency. Experimental study shows that the test cases generated by SparseTG-GS achieve the best attack success rate for target DNNs. The perturbed superpixels in the test cases are fewer and more interpretable. In addition, SparseTG-GS is efficient for generating test cases, especially on large-sized images. The code of SparseTG-GS is available at https://github.com/Yunhelee/SparseTG-GS .

Authors

Institutions

Publication Details

Journal
ACM Transactions on Software Engineering and Methodology
Published
2026-11-18
DOI
https://doi.org/10.1145/3802544
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

SparseTG-GS: Test Case Generation via Sparse Perturbation Group

Hai Dong, Yan Xiao, Pengcheng Zhang, Shunhui Ji et al.
ACM Transactions on Software Engineering and Methodology
Adversarial Robustness in Machine Learning
article

SparseTG-GS: Test Case Generation via Sparse Perturbation Group

Hai Dong, Yan Xiao, Pengcheng Zhang, Shunhui Ji, Yi Xiao, Yunhe Li, Shunhui Ji, Hai Dong, LiMing Hu, Pengcheng Zhang
article en

Abstract

Deep Neural Networks (DNNs) have been widely applied in the field of computer vision. While DNNs exhibit remarkable accuracy in classification tasks, they remain susceptible to adversarial examples. Robustness testing for DNNs has become crucial. Existing test case generation methods suffer from certain limitations, such as dispersed distribution of perturbations, insufficient realism, and high time cost. This article proposes a test case generation method, Sparse Perturbation-Based Test Case Generation—Group-Wise Sparsity (SparseTG-GS). Initially, superpixel segmentation is applied to partition the input image into multiple superpixels. Next, perturbation groups are iteratively introduced into the superpixels until the perturbed image effectively compromises the target DNN. Finally, based on the importance of each perturbation, the initial perturbation scheme is improved by re-adding perturbation groups and minimizing superfluous perturbations and perturbation magnitudes. We improve the AdvGAN framework to construct the Generative Adversarial Networks (GANs) for calculating a perturbation importance matrix for test cases with enhanced optimization efficiency. Experimental study shows that the test cases generated by SparseTG-GS achieve the best attack success rate for target DNNs. The perturbed superpixels in the test cases are fewer and more interpretable. In addition, SparseTG-GS is efficient for generating test cases, especially on large-sized images. The code of SparseTG-GS is available at https://github.com/Yunhelee/SparseTG-GS .

ACM Transactions on Software Engineering and MethodologyVol. 35(12)
Sun Yat-sen University (CN), Hohai University (CN), RMIT University (AU)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon