Unrestricted Adversarial Examples via Semantic Manipulation

Anand Bhattad

ICLR, 2020.

Cited by: 10|Bibtex|Views25|Links
EI
Keywords:
Adversarial Examples Semantic Manipulation Image Colorization Texture Transfer

Abstract:

Machine learning models, especially deep neural networks (DNNs), have been shown to be vulnerable against adversarial examples which are carefully crafted samples with a small magnitude of the perturbation. Such adversarial perturbations are usually restricted by bounding their $\mathcal{L}_p$ norm such that they are imperceptible, and t...More
Your rating :
0

Tags
Comments