Using Metamorphic Testing to Evaluate DNN Coverage Criteria

  • Jinyi Zhou
  • , Kun Qiu
  • , Zheng Zheng
  • , Tsong Yueh Chen
  • , Pak Lok Poon

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Generating test cases and further evaluating their 'quality' are two critical topics in the area of Deep Neural Networks (DNNs). In this domain, different studies (e.g., [1], [2]) have reported that metamorphic testing (MT) serves as an effective test case generation method, where an initial set of source test cases is augmented with identified metamorphic relations (MRs) to produce the corresponding set of follow-up test cases. As a result, the fault detection effectiveness (and, hence, the 'quality') of the resulting test suite T, containing these source and follow-up test cases, will most likely be increased.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE 31st International Symposium on Software Reliability Engineering Workshops, ISSREW 2020
EditorsMarco Vieira, Henrique Madeira, Nuno Antunes, Zheng Zheng
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages147-148
Number of pages2
ISBN (Electronic)9781728198705
DOIs
StatePublished - Oct 2020
Event31st IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2020 - Virtual, Coimbra, Portugal
Duration: 12 Oct 202015 Oct 2020

Publication series

NameProceedings - 2020 IEEE 31st International Symposium on Software Reliability Engineering Workshops, ISSREW 2020

Conference

Conference31st IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2020
Country/TerritoryPortugal
CityVirtual, Coimbra
Period12/10/2015/10/20

Keywords

  • Deep Neural Networks, Metamorphic relations, Coverage criteria, Test adequacy

Fingerprint

Dive into the research topics of 'Using Metamorphic Testing to Evaluate DNN Coverage Criteria'. Together they form a unique fingerprint.

Cite this