randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of →
本文介绍一种面向深度分类器的样本依赖的鲁棒性保证技术——随机平滑;提出了一种非加性和确定性的平滑方法,Deterministic Smoothing with Splitting Noise(DSSN),并通过对CIFAR-10和ImageNet数据集的测试,证明了其比以前的工作具有更高的L_1鲁棒性证明。