Adversarial Attacks on Medical Segmentation Model via Transformation of Feature Statistics
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Woonghee | - |
dc.contributor.author | Ju, Mingeon | - |
dc.contributor.author | Sim, Yura | - |
dc.contributor.author | Jung, Young Kul | - |
dc.contributor.author | Kim, Tae Hyung | - |
dc.contributor.author | Kim, Younghoon | - |
dc.date.accessioned | 2024-04-12T05:30:26Z | - |
dc.date.available | 2024-04-12T05:30:26Z | - |
dc.date.issued | 2024-03 | - |
dc.identifier.issn | 2076-3417 | - |
dc.identifier.issn | 2076-3417 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/118725 | - |
dc.description.abstract | Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models exhibiting remarkable performance. Yet, even with these advances, these models are found to be vulnerable to adversarial attacks, a problem that equally affects automatic CT segmentation models. Conventional adversarial attacks typically rely on adding noise or perturbations, leading to a compromise between the success rate of the attack and its perceptibility. In this study, we challenge this paradigm and introduce a novel generation of adversarial attacks aimed at deceiving both the target segmentation model and medical practitioners. Our approach aims to deceive a target model by altering the texture statistics of an organ while retaining its shape. We employ a real-time style transfer method, known as the texture reformer, which uses adaptive instance normalization (AdaIN) to change the statistics of an image's feature.To induce transformation, we modify the AdaIN, which typically aligns the source and target image statistics. Through rigorous experiments, we demonstrate the effectiveness of our approach. Our adversarial samples successfully pass as realistic in blind tests conducted with physicians, surpassing the effectiveness of contemporary techniques. This innovative methodology not only offers a robust tool for benchmarking and validating automated CT segmentation systems but also serves as a potent mechanism for data augmentation, thereby enhancing model generalization. This dual capability significantly bolsters advancements in the field of deep learning-based medical and healthcare segmentation models. | - |
dc.format.extent | 16 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | MDPI | - |
dc.title | Adversarial Attacks on Medical Segmentation Model via Transformation of Feature Statistics | - |
dc.type | Article | - |
dc.publisher.location | 스위스 | - |
dc.identifier.doi | 10.3390/app14062576 | - |
dc.identifier.scopusid | 2-s2.0-85192577285 | - |
dc.identifier.wosid | 001191326500001 | - |
dc.identifier.bibliographicCitation | Applied Sciences-basel, v.14, no.6, pp 1 - 16 | - |
dc.citation.title | Applied Sciences-basel | - |
dc.citation.volume | 14 | - |
dc.citation.number | 6 | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 16 | - |
dc.type.docType | Article | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Materials Science | - |
dc.relation.journalResearchArea | Physics | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Multidisciplinary | - |
dc.relation.journalWebOfScienceCategory | Engineering, Multidisciplinary | - |
dc.relation.journalWebOfScienceCategory | Materials Science, Multidisciplinary | - |
dc.relation.journalWebOfScienceCategory | Physics, Applied | - |
dc.subject.keywordAuthor | adversarial attacks | - |
dc.subject.keywordAuthor | realistic adversarial samples | - |
dc.subject.keywordAuthor | deep learning-based segmentation | - |
dc.subject.keywordAuthor | computed tomography (CT) segmentation | - |
dc.subject.keywordAuthor | data augmentation | - |
dc.identifier.url | https://www.mdpi.com/2076-3417/14/6/2576 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG 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.