Minority Reports Defense: Defending Against Adversarial Patches

Understand

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.