Authors
Ian J Goodfellow, Jonathon Shlens, Christian Szegedy
Publication date
2014/12/20
Journal
arXiv preprint arXiv:1412.6572
Description
Abstract: Several machine learning models, including neural networks, consistently
misclassify adversarial examples---inputs formed by applying small but intentionally worst-
case perturbations to examples from the dataset, such that the perturbed input results in the
model outputting an incorrect answer with high confidence. Early attempts at explaining this
phenomenon focused on nonlinearity and overfitting. We argue instead that the primary
cause of neural networks' vulnerability to adversarial perturbation is their linear nature. ...
Total citations
20142015201615051
Scholar articles
IJ Goodfellow, J Shlens, C Szegedy - arXiv preprint arXiv:1412.6572, 2014