122 citations · 239 across the 37 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 3 cited
Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions
He Zhao, Trung Le, Paul Montague +3
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, v…
cs.LG2019
When Can Neural Networks Learn Connected Decision Regions?
Trung Le, Dinh Phung
Previous work has questioned the conditions under which the decision regions of a neural network are connected and further showed the implications of the corresponding theory to th…