论文标题
少数民族报告防御：防御对抗斑块
Minority Reports Defense: Defending Against Adversarial Patches
论文作者
论文摘要
深度学习的图像分类很容易受到对抗性攻击的影响，即使攻击者只会更改图像的一小部分。我们提出了针对补丁攻击的防御，基于部分阻塞每个候选补丁位置周围的图像，以使几个闭合完全隐藏了补丁。我们在CIFAR-10，Fashion Mnist和MNIST上证明了我们的防御对一定尺寸的补丁攻击提供了认证的安全性。
Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate patch location, so that a few occlusions each completely hide the patch. We demonstrate on CIFAR-10, Fashion MNIST, and MNIST that our defense provides certified security against patch attacks of a certain size.
