Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revision Both sides next revision
adversarial_training [2018/09/24 17:01]
admin
adversarial_training [2018/11/29 16:26]
admin
Line 298: Line 298:
 This example gives an exponential separation between classical learning and robust learning in the statistical query model. It suggests that adversarial examples may be an unavoidable byproduct of computational limitations of learning algorithms. This example gives an exponential separation between classical learning and robust learning in the statistical query model. It suggests that adversarial examples may be an unavoidable byproduct of computational limitations of learning algorithms.
  
-https://​arxiv.org/​pdf/1809.07802.pdf Playing the Game of Universal Adversarial Perturbations+https://​arxiv.org/​abs/1811.11553v1  
 +Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects 
 + 
 +https://​arxiv.org/​abs/​1809.07802v2 ​Playing the Game of Universal Adversarial Perturbations 
 +