Comment on "Biologically inspired protection of deep networks from adversarial attacks"

Wieland Brendel; Matthias Bethge

Comment on "Biologically inspired protection of deep networks from adversarial attacks"

Machine Learning 2017-04-06 v1 Machine Learning Neurons and Cognition

Authors: Wieland Brendel , Matthias Bethge

Abstract

A recent paper suggests that Deep Neural Networks can be protected from gradient-based adversarial perturbations by driving the network activations into a highly saturated regime. Here we analyse such saturated networks and show that the attacks fail due to numerical limitations in the gradient computations. A simple stabilisation of the gradient estimates enables successful and efficient attacks. Thus, it has yet to be shown that the robustness observed in highly saturated networks is not simply due to numerical limitations.

Keywords

adversarial attacks deep neural networks saturated networks gradient-based perturbations numerical limitations robustness

Cite

@article{arxiv.1704.01547,
  title  = {Comment on "Biologically inspired protection of deep networks from adversarial attacks"},
  author = {Wieland Brendel and Matthias Bethge},
  journal= {arXiv preprint arXiv:1704.01547},
  year   = {2017}
}

Comments

4 pages, 3 figures

Related papers

View all related →

Machine Learning · Statistics

Biologically inspired protection of deep networks from adversarial attacks