Certified Defenses against Adversarial Examples

ICLR, Volume abs/1801.09344, 2018.

Cited by: 325|Bibtex|Views18|Links
EI

Abstract:

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and adversarial training have been proposed, but often followed by new, stronger attacks that defeat these de...More

Code:

Data:

Your rating :
0

 

Tags
Comments