Detecting Deep Neural Network Defects with Data Flow Analysis

Abstract

Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks. However, it is very hard to figure out whether the low precision of a DNN model is an inevitable result, or caused by defects. This paper aims at addressing this challenging problem. We find that the internal data flow footprints of a DNN model can provide insights to locate the root cause effectively. We develop DeepMorph (DNN Tomography) to analyze the root cause, which can guide a DNN developer to improve the model.

2 pages

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Understanding Neural Networks Through Deep Visualization
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Understanding deep learning requires rethinking generalization
• Identifying Implementation Bugs in Machine Learning based Image Classifiers using Metamorphic Testing
• Testing Deep Neural Networks
• TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
• DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
• On the Limitation of MagNet Defense against $L_1$-based Adversarial Examples