Robust CNN Compression Framework for Security-Sensitive Embedded Systems
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jeonghyun | - |
dc.contributor.author | Lee, Sangkyun | - |
dc.date.accessioned | 2022-03-05T00:40:45Z | - |
dc.date.available | 2022-03-05T00:40:45Z | - |
dc.date.created | 2021-12-07 | - |
dc.date.issued | 2021-02 | - |
dc.identifier.issn | 2076-3417 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/137801 | - |
dc.description.abstract | Convolutional neural networks (CNNs) have achieved tremendous success in solving complex classification problems. Motivated by this success, there have been proposed various compression methods for downsizing the CNNs to deploy them on resource-constrained embedded systems. However, a new type of vulnerability of compressed CNNs known as the adversarial examples has been discovered recently, which is critical for security-sensitive systems because the adversarial examples can cause malfunction of CNNs and can be crafted easily in many cases. In this paper, we proposed a compression framework to produce compressed CNNs robust against such adversarial examples. To achieve the goal, our framework uses both pruning and knowledge distillation with adversarial training. We formulate our framework as an optimization problem and provide a solution algorithm based on the proximal gradient method, which is more memory-efficient than the popular ADMM-based compression approaches. In experiments, we show that our framework can improve the trade-off between adversarial robustness and compression rate compared to the existing state-of-the-art adversarial pruning approach. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | MDPI | - |
dc.title | Robust CNN Compression Framework for Security-Sensitive Embedded Systems | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Sangkyun | - |
dc.identifier.doi | 10.3390/app11031093 | - |
dc.identifier.scopusid | 2-s2.0-85100076918 | - |
dc.identifier.wosid | 000691301800001 | - |
dc.identifier.bibliographicCitation | APPLIED SCIENCES-BASEL, v.11, no.3, pp.1 - 17 | - |
dc.relation.isPartOf | APPLIED SCIENCES-BASEL | - |
dc.citation.title | APPLIED SCIENCES-BASEL | - |
dc.citation.volume | 11 | - |
dc.citation.number | 3 | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 17 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
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 | model compression | - |
dc.subject.keywordAuthor | adversarial robustness | - |
dc.subject.keywordAuthor | weight pruning | - |
dc.subject.keywordAuthor | adversarial training | - |
dc.subject.keywordAuthor | distillation | - |
dc.subject.keywordAuthor | embedded system | - |
dc.subject.keywordAuthor | secure AI | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea 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.