Minority Reports Defense: Defending Against Adversarial Patches

Authors: Michael McCoyd, Won Park, Steven Chen, Neil Shah, Ryan Roggenkemper, Minjune Hwang, Jason Xinyu Liu, David Wagner
Published: 2020-04-28

Source: https://arxiv.org/abs/2004.13799

PDF: https://arxiv.org/pdf/2004.13799

Labels Predicted by AI

防御効果分析 攻撃検出 敵対的攻撃検出

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

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.