Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

ADAPTIVE WARPING NETWORK FOR TRANSFERABLE ADVERSARIAL ATTACKS

Full metadata record
DC Field Value Language
dc.contributor.authorSon, Minji-
dc.contributor.authorKwon, Myung-Joon-
dc.contributor.authorKim, Hee-Seon-
dc.contributor.authorByun, Junyoung-
dc.contributor.authorCho, Seungju-
dc.contributor.authorKim, Changick-
dc.date.accessioned2024-02-14T01:30:24Z-
dc.date.available2024-02-14T01:30:24Z-
dc.date.issued2022-
dc.identifier.issn1522-4880-
dc.identifier.urihttps://scholarworks.bwise.kr/cau/handle/2019.sw.cau/72003-
dc.description.abstractDeep Neural Networks (DNNs) are extremely susceptible to adversarial examples, which are crafted by intentionally adding imperceptible perturbations to clean images. Due to potential threats of adversarial attacks in practice, black-box transfer-based attacks are carefully studied to identify the vulnerability of DNNs. Unfortunately, transfer-based attacks often fail to achieve high transferability because the adversarial examples tend to overfit the source model. Applying input transformation is one of the most effective methods to avoid such overfitting. However, most previous input transformation methods obtain limited transferability because these methods utilize fixed transformations for all images. To solve the problem, we propose an Adaptive Warping Network (AWN), which searches for appropriate warping to the individual data. Specifically, AWN optimizes the warping, which mitigates the effect of adversarial perturbations in each iteration. The adversarial examples are generated to become robust against such strong transformations. Extensive experimental results on the ImageNet dataset demonstrate that AWN outperforms the existing input transformation methods in terms of transferability.-
dc.format.extent5-
dc.language영어-
dc.language.isoENG-
dc.publisherIEEE-
dc.titleADAPTIVE WARPING NETWORK FOR TRANSFERABLE ADVERSARIAL ATTACKS-
dc.typeArticle-
dc.identifier.doi10.1109/ICIP46576.2022.9897701-
dc.identifier.bibliographicCitation2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, pp 3056 - 3060-
dc.description.isOpenAccessN-
dc.identifier.wosid001058109503030-
dc.identifier.scopusid2-s2.0-85146732188-
dc.citation.endPage3060-
dc.citation.startPage3056-
dc.citation.title2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP-
dc.type.docTypeProceedings Paper-
dc.publisher.location미국-
dc.subject.keywordAuthorAdversarial Attacks-
dc.subject.keywordAuthorTransfer-based Attacks-
dc.subject.keywordAuthorTransferability-
dc.subject.keywordAuthorInput Transformation-
dc.subject.keywordAuthorWarping-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.description.journalRegisteredClassscopus-
Files in This Item
There are no files associated with this item.
Appears in
Collections
ETC > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Byun, Junyoung photo

Byun, Junyoung
대학원 (통계데이터사이언스학과)
Read more

Altmetrics

Total Views & Downloads

BROWSE