Search Results for author:
Found 1 papers, 0 papers with code
Adaptive Perturbation for Adversarial Attack
Instead of using the sign function, we propose to directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
