Test Optimization in DNN Testing: A Survey-Reference-Cited by-同舟云学术

Test Optimization in DNN Testing: A Survey

Published:2024-01-27 Issue: Volume: Page:
ISSN:1049-331X
Container-title:ACM Transactions on Software Engineering and Methodology
language:en
Short-container-title:ACM Trans. Softw. Eng. Methodol.

Author:

Hu Qiang¹,Guo Yuejun²,Xie Xiaofei³,Cordy Maxime⁴,Ma Lei⁵,Papadakis Mike¹,Le Traon Yves¹

Affiliation:

1. University of Luxembourg, Esch-sur-Alzette, Luxembourg

2. Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg

3. Singapore Management University, Singapore

4. University of Luxembourg, Luxembourg

5. The University of Tokyo, Japan & University of Albert, Edmonton, Canada

Abstract

This paper presents a comprehensive survey on test optimization in deep neural network (DNN) testing. Here, test optimization refers to testing with low data labeling effort. We analyzed 90 papers, including 43 from the software engineering (SE) community, 32 from the machine learning (ML) community, and 15 from other communities. Our study: (i) unifies the problems as well as terminologies associated with low-labeling cost testing, (ii) compares the distinct focal points of SE and ML communities, and (iii) reveals the pitfalls in existing literature. Furthermore, we highlight the research opportunities in this domain.

Publisher

Association for Computing Machinery (ACM)

Subject

Software

Link

https://dl.acm.org/doi/pdf/10.1145/3643678

Reference127 articles.

1. Black-Box Testing of Deep Neural Networks through Test Case Diversity

2. Zohreh Aghababaeyan, Manel Abdellatif, Mahboubeh Dadkhah, and Lionel Briand. 2023. DeepGD: a multi-objective black-box test selection approach for deep neural networks. arxiv:2303.04878 [cs.LG] https://arxiv.org/pdf/2303.04878.pdf Accessed on January 23rd, 2024.

3. Jonathan Aigrain and Marcin Detyniecki. 2019. Detecting adversarial examples and other misclassifications in neural networks by introspection. arxiv:1905.09186 [cs.LG] https://arxiv.org/pdf/1905.09186.pdf Accessed on January 23rd, 2024.

4. Hamzah Al-Qadasi, Changshun Wu, Yliès Falcone, and Saddek Bensalem. 2022. DeepAbstraction: 2-level prioritization for unlabeled test inputs in deep neural networks. In IEEE International Conference On Artificial Intelligence Testing (AITest) (Newark, CA, USA). IEEE, Piscataway, NJ, USA, 64–71. https://doi.org/10.1109/AITest55621.2022.00018

5. Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering