Data Sanity Check for Deep Learning Systems via Learnt Assertions [article]

Haochuan Lu and Huanlin Xu and Nana Liu and Yangfan Zhou and Xin Wang
2019 arXiv   pre-print
Reliability is a critical consideration to DL-based systems. But the statistical nature of DL makes it quite vulnerable to invalid inputs, i.e., those cases that are not considered in the training phase of a DL model. This paper proposes to perform data sanity check to identify invalid inputs, so as to enhance the reliability of DL-based systems. We design and implement a tool to detect behavior deviation of a DL model when processing an input case. This tool extracts the data flow footprints
more » ... d conducts an assertion-based validation mechanism. The assertions are built automatically, which are specifically-tailored for DL model data flow analysis. Our experiments conducted with real-world scenarios demonstrate that such an assertion-based data sanity check mechanism is effective in identifying invalid input cases.
arXiv:1909.03835v3 fatcat:5e2pvqaquvalvgoko4e36f7jqq