[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的論文Intriguing properties of neural networks
論文下載到本地的第3篇
[3]Ian Goodfellow對對抗樣本解釋的論文Explaining and Harnessing Adversarial Examples
論文下載到本地的第5篇
[4]最近Bengio他們組發文表示就算是從相機自然采集的圖像，也會有這種特性Adversarial examples in the physical world
論文下載到本地第4篇
[5]Anh Nguyen等人在CVPR2015上首次提出Fooling Examples的論文Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
https://arxiv.org/pdf/1412.1897.pdf
下載為本地論文第18篇
[6]Delving into Transferable Adversarial Examples and Black-box Attacks
論文下載到本地的第17篇
對抗樣本可轉移性與黑盒攻擊_學習筆記：https://blog.csdn.net/qq_35414569/article/details/82383788