Data Sanity Check for Deep Learning Systems via Learnt Assertions
arXiv:1909.03835
Abstract
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.
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- DeepXplore: Automated Whitebox Testing of Deep Learning Systems
- Convolutional Neural Networks for Sentence Classification
- Testing Deep Neural Networks
- TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
- DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks