[1]Karparthy博客 Breaking Linear Classifiers on ImageNet
http://karpathy.github.io/2015/03/30/breaking-convnets/
[2]Christian等人在ICLR2014最先提出adversarial examples的论文Intriguing properties of neural networks
论文下载到本地的第3篇
[3]Ian Goodfellow对对抗样本解释的论文Explaining and Harnessing Adversarial Examples
论文下载到本地的第5篇
[4]最近Bengio他们组发文表示就算是从相机自然采集的图像，也会有这种特性Adversarial examples in the physical world
论文下载到本地第4篇
[5]Anh Nguyen等人在CVPR2015上首次提出Fooling Examples的论文Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
https://arxiv.org/pdf/1412.1897.pdf
下载为本地论文第18篇
[6]Delving into Transferable Adversarial Examples and Black-box Attacks
论文下载到本地的第17篇
对抗样本可转移性与黑盒攻击_学习笔记：https://blog.csdn.net/qq_35414569/article/details/82383788