CAAD 2018：基于对抗变换网络的强力无访问黑盒攻击
机器学习
2018-11-06 v1 机器学习
摘要
在本文中，我们提出对对抗变换网络（Adversarial Transformation Networks, ATN）的改进以生成对抗样本，该样本能够以最先进的性能欺骗白盒模型与黑盒模型，并在 CAAD 2018 的无目标任务中获得第二名。
引用
@article{arxiv.1811.01225,
title = {CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network},
author = {Xiaoyi Dong and Weiming Zhang and Nenghai Yu},
journal= {arXiv preprint arXiv:1811.01225},
year = {2018}
}