论文标题
半靠背繁殖的加速对抗扰动50％
Accelerating Adversarial Perturbation by 50% with Semi-backward Propagation
论文作者
论文摘要
对抗扰动在对抗鲁棒性领域起着重要作用，该领域解决了输入数据上的最大化问题。我们表明，这种优化的向后传播可以加速$ 2 \ times $（因此，包括远期传播在内的总体优化可以加速$ 1.5 \ times $），而无需任何效用，如果我们只计算输出梯度，而不是在向后传播期间参数梯度。
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 $2\times$ (and thus the overall optimization including the forward propagation can accelerate $1.5\times$), without any utility drop, if we only compute the output gradient but not the parameter gradient during the backward propagation.
