Home > Research > Publications & Outputs > Concolic testing for deep neural networks


Text available via DOI:

View graph of relations

Concolic testing for deep neural networks

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

  • Youcheng Sun
  • Min Wu
  • Wenjie Ruan
  • Xiaowei Huang
  • Marta Kwiatkowska
  • Daniel Kroening
Publication date3/09/2018
Host publicationProceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, ASE 2018, Montpellier, France, September 3-7, 2018
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Number of pages11
ISBN (Print)9781450359375
<mark>Original language</mark>English


Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. In this paper, we develop the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, we utilise quantified linear arithmetic over rationals to express test requirements that have been studied in the literature, and then develop a coherent method to perform concolic testing with the aim of better coverage. Our experimental results show the effectiveness of the concolic testing approach in both achieving high coverage and finding adversarial examples.