Minority Reports Defense: Defending Against Adversarial Patches
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 3 references indexed in Scilit: