Deep Learning Adversarial Examples – Clarifying Misconceptions (kdnuggets.com) 1 points by SergeyHack 10y ago ↗ HN
[–] SergeyHack 10y ago ↗ 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."
1 comment
[ 8.1 ms ] story [ 21.2 ms ] thread"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."