← Search

David Andersen

1 accepted papers

2019

TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

ICML 2019oral

Neural networks are difficult to interpret and debug. We introduce testing techniques for neural networks that can discover errors occurring only for rare inputs. Specifically, we develop coverage-guided fuzzing (CGF) methods for neural networks. In CGF, random mutations of inputs are guided by a co…