Effective white-box testing of deep neural networks with adaptive neuron-selection strategy

Seokhyun Lee, Sooyoung Cha, Dain Lee, Hakjoo Oh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present Adapt, a new white-box testing technique for deep neural networks. As deep neural networks are increasingly used in safety-first applications, testing their behavior systematically has become a critical problem. Accordingly, various testing techniques for deep neural networks have been proposed in recent years. However, neural network testing is still at an early stage and existing techniques are not yet sufficiently effective. In this paper, we aim to advance this field, in particular white-box testing approaches for neural networks, by identifying and addressing a key limitation of existing state-of-the-arts. We observe that the so-called neuron-selection strategy is a critical component of white-box testing and propose a new technique that effectively employs the strategy by continuously adapting it to the ongoing testing process. Experiments with real-world network models and datasets show that Adapt is remarkably more effective than existing testing techniques in terms of coverage and adversarial inputs found.

Original languageEnglish
Title of host publicationISSTA 2020 - Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis
EditorsSarfraz Khurshid, Corina S. Pasareanu
PublisherAssociation for Computing Machinery, Inc
Pages165-176
Number of pages12
ISBN (Electronic)9781450380089
DOIs
Publication statusPublished - 2020 Jul 18
Event29th ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2020 - Virtual, Online, United States
Duration: 2020 Jul 182020 Jul 22

Publication series

NameISSTA 2020 - Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis

Conference

Conference29th ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2020
CountryUnited States
CityVirtual, Online
Period20/7/1820/7/22

Keywords

  • Deep neural networks
  • Online learning
  • White-box testing

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Effective white-box testing of deep neural networks with adaptive neuron-selection strategy'. Together they form a unique fingerprint.

Cite this