Two-Stage Image Restoration: A Shield against Adversarial Attacks on Face Identification
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lim, Min Young | - |
dc.contributor.author | Min Hong, Pyo | - |
dc.contributor.author | Lee, Youn Kyu | - |
dc.date.accessioned | 2024-03-06T10:00:20Z | - |
dc.date.available | 2024-03-06T10:00:20Z | - |
dc.date.issued | 2023 | - |
dc.identifier.issn | 2162-1233 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/32724 | - |
dc.description.abstract | Various methods have been proposed to defend face identification systems against adversarial attacks by eliminating adversarial perturbations from target face images. However, it is challenging to eliminate such perturbations while preserving the crucial facial features within the images. In this paper, we propose a novel purification method for an effective defense against adversarial attacks on target face images. Our method incorporates a two-stage image restoration utilizing diffusion, consisting of sequential super-resolution-based image restoration followed by colorization-based image restoration. The experimental results demonstrate the effectiveness of our method in eliminating perturbations while preserving the identity of the facial features. © 2023 IEEE. | - |
dc.format.extent | 3 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Two-Stage Image Restoration: A Shield against Adversarial Attacks on Face Identification | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/ICTC58733.2023.10393701 | - |
dc.identifier.scopusid | 2-s2.0-85184578352 | - |
dc.identifier.bibliographicCitation | International Conference on ICT Convergence, pp 1283 - 1285 | - |
dc.citation.title | International Conference on ICT Convergence | - |
dc.citation.startPage | 1283 | - |
dc.citation.endPage | 1285 | - |
dc.type.docType | Conference paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | defense against adversarial attacks | - |
dc.subject.keywordAuthor | face identification | - |
dc.subject.keywordAuthor | image restoration | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
94, Wausan-ro, Mapo-gu, Seoul, 04066, Korea02-320-1314
COPYRIGHT 2020 HONGIK UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.