Prefer a chat interface with context about you and your work?
Witchcraft: Efficient PGD Attacks with Random Step Size
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods without restarts trade off performance for computational efficiency because they do not adequately explore the image space and are highly sensitive to the choice of step size. We propose …