Efficient Defenses Against Adversarial Attacks Efficient Defenses Against Adversarial Attacks
Paper summary Zantedschi et al. propose Gaussian data augmentation in conjunction with bounded $\text{ReLU}$ activations as defense strategy against adversarial examples. Here, Gaussian data augmentation refers to the practice of adding Gaussian noise to the input during training.
arxiv.org
arxiv-sanity.com
scholar.google.com
Efficient Defenses Against Adversarial Attacks
Valentina Zantedeschi and Maria-Irina Nicolae and Ambrish Rawat
arXiv e-Print archive - 2017 via Local arXiv
Keywords: cs.LG

more

Summary by David Stutz 5 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and