对抗攻击与防御竞赛
计算机视觉与模式识别
2018-04-03 v1 密码学与安全
机器学习
机器学习
摘要
为加速对抗样本与机器学习分类器鲁棒性的研究，Google Brain 组织了 NIPS 2017 竞赛，鼓励研究者开发生成对抗样本的新方法以及抵御对抗样本的新手段。在本章中，我们描述了该竞赛的结构与组织，以及若干排名靠前团队所提出的解决方案。
引用
@article{arxiv.1804.00097,
title = {Adversarial Attacks and Defences Competition},
author = {Alexey Kurakin and Ian Goodfellow and Samy Bengio and Yinpeng Dong and Fangzhou Liao and Ming Liang and Tianyu Pang and Jun Zhu and Xiaolin Hu and Cihang Xie and Jianyu Wang and Zhishuai Zhang and Zhou Ren and Alan Yuille and Sangxia Huang and Yao Zhao and Yuzhe Zhao and Zhonglin Han and Junjiajia Long and Yerkebulan Berdibekov and Takuya Akiba and Seiya Tokui and Motoki Abe},
journal= {arXiv preprint arXiv:1804.00097},
year = {2018}
}
备注
36 pages, 10 figures