Deep Validation: Toward Detecting Real-world Corner Cases for Deep Neural Networks
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractThe exceptional performance of Deep neural networks (DNNs) encourages their deployment in safety-And dependability-critical systems. However, DNNs often demonstrate erroneous behaviors in real-world corner cases. Existing countermeasures center on improving the testing and bug-fixing practice. Unfortunately, building a bug-free DNN-based system is almost impossible currently due to its black-box nature, so anomaly detection is imperative in practice. Motivated by the idea of data validation in a traditional program, we propose and implement Deep Validation, a novel framework for detecting real-world error-inducing corner cases in a DNN-based system during runtime. We model the specifications of DNNs by resorting to their training data and cast checking input validity of DNNs as the problem of discrepancy estimation. Deep Validation achieves excellent detection results against various corner case scenarios across three popular datasets. Consequently, Deep Validation greatly complements existing efforts and is a crucial step toward building safe and dependable DNN-based systems.
Acceptance Date15/03/2019
All Author(s) ListWeibin Wu, Hui Xu, Sanqiang Zhong, Michael R Lyu, Irwin King
Name of Conference49th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)
Start Date of Conference24/06/2019
End Date of Conference27/06/2019
Place of ConferencePortland, USA
Country/Region of ConferenceUnited States of America
Proceedings TitleProceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2019
Pages125 - 137
LanguagesEnglish-United States

Last updated on 2021-10-05 at 23:58