Learning Universal Adversarial Perturbations with Generative Models release_sb4e7l3kxrgqdi7nrgkhmesfiu

by Jamie Hayes, George Danezis

Released as a article .

2017  

Abstract

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and classifier, there exists so called universal adversarial perturbations, a single perturbation that causes a misclassification when applied to any input. In this work, we introduce universal adversarial networks, a generative network that is capable of fooling a target classifier when it's generated output is added to a clean sample from a dataset. We show that this technique improves on known universal adversarial attacks.
In text/plain format

Archived Files and Locations

application/pdf  1.7 MB
file_nr2jrcscszgjnetizub6ytubw4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-08-17
Version   v1
Language   en ?
arXiv  1708.05207v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: c94fa419-a6e8-41e1-aed1-82f9ac5056dd
API URL: JSON