Deep Learning Adversarial Examples – Clarifying Misconceptions

[SergeyHack]

http://www.kdnuggets.com/2015/07/deep-learning-adversarial-examples-misconceptions.html

[SergeyHack]

The 6th point is very interesting:

"Adversarial examples generalize across models trained to perform the same task, even if those models have different architectures and were trained on a different training set."