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 li...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE) s. 109 - 119
Hlavní autoři: Sun, Youcheng, Wu, Min, Ruan, Wenjie, Huang, Xiaowei, Kwiatkowska, Marta, Kroening, Daniel
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 01.09.2018
Témata:
Artificial neural networks
concolic testing
Measurement
neural networks
Robustness
Scholarships
Software engineering
Software tools
symbolic execution
Testing
ISSN:2643-1572
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:2643-1572
DOI:10.1145/3238147.3238172