BriefGPT.xyz
May, 2019
对抗鲁棒性在扰动类型之间的转移
Transfer of Adversarial Robustness Between Perturbation Types
HTML
PDF
Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt
TL;DR
研究对抗网络的对抗鲁棒性在不同扰动类型之间的转移，结果表明评估广泛范围的扰动大小是必要的，并建议在不同类型和大小的扰动下进行对抗防御的评估。
Abstract
We study the transfer of
adversarial robustness
of
deep neural networks
between different
perturbation types
. While most work on adversari
→