BriefGPT.xyz
Nov, 2018
双边对抗训练:快速训练更健壮的模型以抵御对抗性攻击
Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
HTML
PDF
Jianyu Wang
TL;DR
本文提出了一种Bilateral Adversarial Training方法,使用一步定向攻击生成对抗样本来训练一个抗攻击性更强的神经网络,实验结果表明该方法对于对抗性攻击的鲁棒性有显著提升。
Abstract
In this paper, we study fast training of adversarially robust models. From the analyses on the state-of-the-art defense method, i.e., the multi-step
adversarial training
~\cite{madry2017towards}, we hypothesize that the
→