Exposing previously undetectable faults in deep neural networks

Existing methods for testing DNNs solve the oracle problem by constraining the raw features (e.g. image pixel values) to be within a small distance of a dataset example for which the desired DNN output is known. But this limits the kinds of faults these approaches are able to detect. In this paper,...

ver descrição completa

Detalhes bibliográficos
Principais autores: Dunn, I, Pouget, H, Kroening, D, Melham, T
Formato: Conference item
Idioma:English
Publicado em: Association for Computing Machinery 2021