Home
Biography
Teaching
Research
Publication
Team
Contact
Light
Dark
Automatic
Adversarial Example
SPAT: Semantic-Preserving Adversarial Transformation for Perceptually Similar Adversarial Examples
We propose a novel Semantic-Preserving Adversarial Transformation (SPAT) framework which facilitates an advantageous trade-off between the attack success rate and the perceptual similarity between the benign and adversarial examples.
Cite
×