Defensive Distillation is Not Robust to Adversarial Examples
arXiv:1607.04311
Abstract
We show that defensive distillation is not secure: it is no more resistant to targeted misclassification attacks than unprotected neural networks.
arXiv:1607.04311
We show that defensive distillation is not secure: it is no more resistant to targeted misclassification attacks than unprotected neural networks.