Concolic testing for deep neural networks
Concolic testing for deep neural networks
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. This paper presents the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, we formalise coverage criteria for DNNs that have been studied in the literature, and then develop a coherent method for performing concolic testing to increase test coverage. Our experimental results show the effectiveness of the concolic testing approach in both achieving high coverage and finding adversarial examples.
- Lancaster University United Kingdom
- University of Oxford United Kingdom
- Queen's University Belfast United Kingdom
- University of Liverpool United Kingdom
- University of Salford United Kingdom
Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Software Engineering, Statistics - Machine Learning, Machine Learning (stat.ML), 004, Machine Learning (cs.LG)
Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Software Engineering, Statistics - Machine Learning, Machine Learning (stat.ML), 004, Machine Learning (cs.LG)
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).235 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Top 0.1% influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Top 1% impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Top 1%
Citations provided by BIP!Popularity provided by BIP!