UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning Universal Adversarial Perturbations with Generative Models

Hayes, J; Danezis, G; (2018) Learning Universal Adversarial Perturbations with Generative Models. In: Proceedings of the Security and Privacy Workshops (SPW) 2018 IEEE. (pp. pp. 43-49). IEEE: San Francisco (CA), USA. Green open access

[thumbnail of Danezis_Learning universal adversarial perturbations with generative models_AAM.pdf]
Preview
Text
Danezis_Learning universal adversarial perturbations with generative models_AAM.pdf - Accepted Version

Download (5MB) | Preview

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.

Type: Proceedings paper
Title: Learning Universal Adversarial Perturbations with Generative Models
Event: Security and Privacy Workshops (SPW)
Location: San Francisco (CA), USA
Dates: 24th May 2018
ISBN-13: 978-1-5386-8276-0
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/SPW.2018.00015
Publisher version: https://doi.org/10.1109/SPW.2018.00015
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Perturbation methods, Measurement, Training, Error analysis, Atmospheric modeling, Security, Machine learning
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10059181
Downloads since deposit
144Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item