Accelerating Adversarial Perturbation by 50 Propagation
Adversarial perturbation plays a significant role in the field of adversarial robustness, which solves a maximization problem over the input data. We show that the backward propagation of such optimization can accelerate 2× (and thus the overall optimization including the forward propagation can accelerate 1.5×), without any utility drop, if we only compute the output gradient but not the parameter gradient during the backward propagation.
READ FULL TEXT