Data sanity check for deep learning systems via learnt assertions
H Lu, H Xu, N Liu, Y Zhou, X Wang - arXiv preprint arXiv:1909.03835, 2019 - arxiv.org
H Lu, H Xu, N Liu, Y Zhou, X Wang
arXiv preprint arXiv:1909.03835, 2019•arxiv.orgReliability is a critical consideration to DL-based systems. But the statistical nature of DL
makes it quite vulnerable to invalid inputs, ie, 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 and conducts an assertion-based validation …
makes it quite vulnerable to invalid inputs, ie, 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 and conducts an assertion-based validation …
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 and 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.org
Showing the best result for this search. See all results