DeepConcolic: Testing and Debugging Deep Neural Networks

Deep neural networks (DNNs) have been deployed in a wide range of applications. We introduce a DNN testing and debugging tool, called DeepConcolic, which is able to detect errors with sufficient rigour so as to be applicable to the testing of DNNs in safety-related applications. DeepConcolic is the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE/ACM International Conference on Software Engineering Companion. Online) s. 111 - 114
Hlavní autoři: Sun, Youcheng, Huang, Xiaowei, Kroening, Daniel, Sharp, James, Hill, Matthew, Ashmore, Rob
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.05.2019
Témata:
concolic testing
Debugging
deep neural networks
Engines
Measurement
Neurons
Safety
test coverage criteria
Testing
ISSN:2574-1934
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Deep neural networks (DNNs) have been deployed in a wide range of applications. We introduce a DNN testing and debugging tool, called DeepConcolic, which is able to detect errors with sufficient rigour so as to be applicable to the testing of DNNs in safety-related applications. DeepConcolic is the first tool that implements a concolic testing technique for DNNs, and the first testing tool that provides users with the functionality of investigating particular parts of a DNN. The tool has been made publicly available and a demo video can be found at https://youtu.be/rliynbhoNLM.
ISSN:2574-1934
DOI:10.1109/ICSE-Companion.2019.00051