This is an annotated bibliographies investigating security, privacy, and robustness of machine learning algorithms in adversarial environments.
Intriguing properties of neural networks.
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus. arxiv 2013.
https://arxiv.org/abs/1312.6199
The original. TBD.
Explaining and Harnessing Adversarial Examples
Ian Goodfellow, Jonathon Shlens, Christian Szegedy. ICLR 2014
https://arxiv.org/abs/1412.6572
TBD
TODO:
Add more papers and their tldr.