loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Kyrylo Rudavskyy and Ali Miri

Affiliation: Department of Computer Science, Ryerson University, Toronto, Canada

Keyword(s): Machine Learning, Generative Adversarial Network, Adversarial Attack, Security.

Abstract: The goal of this paper is to explore the resilience of Generative Adversarial Networks(GANs) against adversarial attacks. Specifically, we evaluated the threat potential of an adversarial attack against the discriminator part of the system. Such an attack aims to distort the output by injecting maliciously modified input during training. The attack was empirically evaluated against four types of GANs, injections of 10% and 20% malicious data, and two datasets. The targets were CGAN, ACGAN, WGAN, and WGAN-GP. The datasets were MNIST and F-MNIST. The attack was created by improving an existing attack on GANs. The lower bound for the injection size turned out to be 10% for the improvement and 10-20% for the baseline attack. It was shown that the attack on WGAN-GP can overcome a filtering defence for F-MNIST.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.119.104.238

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Rudavskyy, K. and Miri, A. (2022). Resilience of GANs against Adversarial Attacks. In Proceedings of the 19th International Conference on Security and Cryptography - SECRYPT; ISBN 978-989-758-590-6; ISSN 2184-7711, SciTePress, pages 390-397. DOI: 10.5220/0011307200003283

@conference{secrypt22,
author={Kyrylo Rudavskyy. and Ali Miri.},
title={Resilience of GANs against Adversarial Attacks},
booktitle={Proceedings of the 19th International Conference on Security and Cryptography - SECRYPT},
year={2022},
pages={390-397},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011307200003283},
isbn={978-989-758-590-6},
issn={2184-7711},
}

TY - CONF

JO - Proceedings of the 19th International Conference on Security and Cryptography - SECRYPT
TI - Resilience of GANs against Adversarial Attacks
SN - 978-989-758-590-6
IS - 2184-7711
AU - Rudavskyy, K.
AU - Miri, A.
PY - 2022
SP - 390
EP - 397
DO - 10.5220/0011307200003283
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic