DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Youngwoo | ko |
dc.contributor.author | Han, Donghyeon | ko |
dc.contributor.author | Kim, Changhyeon | ko |
dc.contributor.author | Yoo, Hoi-Jun | ko |
dc.date.accessioned | 2020-05-26T09:20:06Z | - |
dc.date.available | 2020-05-26T09:20:06Z | - |
dc.date.created | 2020-05-25 | - |
dc.date.created | 2020-05-25 | - |
dc.date.created | 2020-05-25 | - |
dc.date.issued | 2020-05 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, v.67, no.5, pp.846 - 850 | - |
dc.identifier.issn | 1549-7747 | - |
dc.identifier.uri | http://hdl.handle.net/10203/274310 | - |
dc.description.abstract | A low-power, highly secure, always-on face recognition (FR) processor is required for security applications. In this brief, a branch net-based early stopping FR (BESF) processor is proposed to prevent adversarial attacks for high security and consume low power for always-on operation. It shows a recognition accuracy of 83.10% under the fast gradient signed method (FGSM), and 71.97% under the projected gradient descent (PGD) attack. The clock-gating of the BESF processor reduces the average power consumption by 30.85%. The unified pointwise and depthwise convolution processing element adopts layer-fusion to reduce the external memory access by 88.0%. Furthermore, noise injection layers are inserted between every bottleneck layer to further reduce the FGSM and PGD attack success rate by 9.29% and 20.0%, respectively. Implemented with a 65 nm CMOS process with a 3.0 mm $\times $ 3.0 mm area, the processor consumes 0.22-0.89 mW power at 1 fps and shows 95.5% FR accuracy in the Labeled Faces in the Wild dataset. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | A 0.22-0.89 mW Low-Power and Highly-Secure Always-On Face Recognition Processor With Adversarial Attack Prevention | - |
dc.type | Article | - |
dc.identifier.wosid | 000531324100010 | - |
dc.identifier.scopusid | 2-s2.0-85084301352 | - |
dc.type.rims | ART | - |
dc.citation.volume | 67 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 846 | - |
dc.citation.endingpage | 850 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS | - |
dc.identifier.doi | 10.1109/TCSII.2020.2980022 | - |
dc.contributor.localauthor | Yoo, Hoi-Jun | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Adversarial attack | - |
dc.subject.keywordAuthor | convolutional neural network | - |
dc.subject.keywordAuthor | external memory access | - |
dc.subject.keywordAuthor | face recognition | - |
dc.subject.keywordAuthor | layer fusion | - |
dc.subject.keywordAuthor | noise injection | - |
dc.subject.keywordAuthor | robustness | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.