论文标题
利用对抗性示例，以惊人的简单防御
Harnessing adversarial examples with a surprisingly simple defense
论文作者
论文摘要
我介绍了一种非常简单的方法来防御对抗性例子。基本思想是在测试时间提高Relu功能的斜率。对MNIST和CIFAR-10数据集进行的实验证明了拟议的防御能够针对未靶向和有针对性设置中的许多强烈攻击的有效性。虽然也许不像最先进的对抗性防御能力那样有效，但这种方法可以提供见解，以理解和减轻对抗性攻击。它也可以与其他防御措施一起使用。
I introduce a very simple method to defend against adversarial examples. The basic idea is to raise the slope of the ReLU function at the test time. Experiments over MNIST and CIFAR-10 datasets demonstrate the effectiveness of the proposed defense against a number of strong attacks in both untargeted and targeted settings. While perhaps not as effective as the state of the art adversarial defenses, this approach can provide insights to understand and mitigate adversarial attacks. It can also be used in conjunction with other defenses.
