연합학습에서의 백도어 공격에 대한 방어 기법 연구
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 권용석 | - |
dc.contributor.author | 안세영 | - |
dc.contributor.author | 김수형 | - |
dc.contributor.author | 조성현 | - |
dc.date.accessioned | 2023-08-22T01:32:10Z | - |
dc.date.available | 2023-08-22T01:32:10Z | - |
dc.date.issued | 2022-06 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/114434 | - |
dc.description.abstract | Federated Learning (FL) is a novel learning paradigm that trains a model cooperatively. In FL, participants can train the model without sharing their data. However, it means the model is vulnerable to backdoor attack. Through the backdoor attack, the attacker can manipulate the output of the model with certain features. To address the problem, backdoor defense methods have been studied. In this paper, we introduce and analyze the studies. Moreover, future research issues are presented at the end of the paper. | - |
dc.format.extent | 4 | - |
dc.language | 한국어 | - |
dc.language.iso | KOR | - |
dc.publisher | 대한전자공학회 | - |
dc.title | 연합학습에서의 백도어 공격에 대한 방어 기법 연구 | - |
dc.title.alternative | A Study on Backdoor Defense Methods in Federated Learning | - |
dc.type | Article | - |
dc.publisher.location | 대한민국 | - |
dc.identifier.bibliographicCitation | 2022년 대한전자공학회 하계학술대회 논문집, pp 2219 - 2222 | - |
dc.citation.title | 2022년 대한전자공학회 하계학술대회 논문집 | - |
dc.citation.startPage | 2219 | - |
dc.citation.endPage | 2222 | - |
dc.type.docType | Proceeding | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.identifier.url | https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11132917 | - |
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.