[paper]Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

本文提出了一個防禦算法，在不改變深度神經網絡的結構並且在儘可能小的影響模型準確率的前提下能夠有效地抵禦對抗樣本的攻擊。 We use the knowledge extracted during distillation to reduce the amplitude of network gradients exploited by adversaries to craft adversaria

>>阅读原文<<