原文:Generating Adversarial Examples with Adversarial Networks

Generating Adversarial Examples with Adversarial Networks : : Paper:IJCAI Code:https: github.com mathcbc advGAN pytorch . Background and Motivation: 为了更加高效的生成对抗样本,本文提出: . 一个前向网络来生成干扰,从而得到多样性的对抗样本 . 一个 ...

2020-03-08 22:41 0 675 推荐指数:

查看详情

论文阅读 | Generating Fluent Adversarial Examples for Natural Languages

Generating Fluent Adversarial Examples for Natural Languages ACL 2019 为自然语言生成流畅的对抗样本 摘要 有效地构建自然语言处理(NLP)任务的对抗性攻击者是一个真正的挑战。首先,由于句子空间是离散的。沿梯度方向 ...

Thu Aug 15 03:56:00 CST 2019 2 408
Adversarial Examples Improve Image Recognition

Xie C, Tan M, Gong B, et al. Adversarial Examples Improve Image Recognition.[J]. arXiv: Computer Vision and Pattern Recognition, 2019. @article ...

Thu Mar 12 22:59:00 CST 2020 0 1086
ICLR2015_Explaining and Harnessing Adversarial Examples

Author 一作: Ian Goodfellow 三作: Christian Szegedy Abstract 之前认为对抗样本对模型的欺骗性是因为模型的高度非线性和过拟合,本文证明了模型 ...

Thu Mar 15 00:51:00 CST 2018 0 940
 
粤ICP备18138465号  © 2018-2025 CODEPRJ.COM