· 2018
Concolic testing for deep neural networks
- 330citations
- 2018year
Short summary
A novel concolic testing approach, combining execution and symbolic analysis, achieves high coverage and finds adversarial examples in Deep Neural Networks (DNNs).
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces the first concolic testing approach for Deep Neural Networks (DNNs).
- Combines program execution and symbolic analysis to explore DNN execution paths.
- Utilizes quantified linear arithmetic over rationals for test requirements.
- Experimental results show high coverage and successful identification of adversarial examples.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source., 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Software
SoftwareComputer Science