Multigenerational Crumpling of 2D Materials for Anticounterfeiting Patterns with Deep Learning Authentication

Lin Jing; Qian Xie; Hongling Li; Kerui Li; Haitao Yang; Patricia Li Ping Ng; Shuo Li; Yang Li; Edwin Hang Tong Teo; Xiaonan Wang; Po Yen Chen

doi:10.1016/j.matt.2020.10.005

Multigenerational Crumpling of 2D Materials for Anticounterfeiting Patterns with Deep Learning Authentication

Lin Jing, Qian Xie, Hongling Li, Kerui Li, Haitao Yang, Patricia Li Ping Ng, Shuo Li, Yang Li, Edwin Hang Tong Teo, Xiaonan Wang, Po Yen Chen

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

Multigenerational 2D-material (2DM) microstructures are fabricated via sequential deformations in a transfer-free fashion and exhibit physical unclonable function patterns with algorithm-recognizable features. Deep learning (DL)-facilitated software is developed on the basis of the “classification and validation” mechanism to shorten the authentication time. With 2DM tags and DL software, a reliable and environmentally stable anticounterfeiting technology, DeepKey, is realized to show superior encoding capacity and fast authentication, which can be applied as an add-on covert layer for QR codes to provide two-layer information security.

Original language	English
Pages (from-to)	2160-2180
Number of pages	21
Journal	Matter
Volume	3
Issue number	6
DOIs	https://doi.org/10.1016/j.matt.2020.10.005
State	Published - 2 Dec 2020
Externally published	Yes

Keywords

MAP4: Demonstrate
anticounterfeiting
deep learning
graphene oxide
hierarchical microstructures
physical unclonable functions
titanium carbide TiCT MXene

Access to Document

10.1016/j.matt.2020.10.005

Cite this

@article{5cd3bf8e9d97498ebfdd6c8bb79fc779,

title = "Multigenerational Crumpling of 2D Materials for Anticounterfeiting Patterns with Deep Learning Authentication",

abstract = "Multigenerational 2D-material (2DM) microstructures are fabricated via sequential deformations in a transfer-free fashion and exhibit physical unclonable function patterns with algorithm-recognizable features. Deep learning (DL)-facilitated software is developed on the basis of the “classification and validation” mechanism to shorten the authentication time. With 2DM tags and DL software, a reliable and environmentally stable anticounterfeiting technology, DeepKey, is realized to show superior encoding capacity and fast authentication, which can be applied as an add-on covert layer for QR codes to provide two-layer information security.",

keywords = "MAP4: Demonstrate, anticounterfeiting, deep learning, graphene oxide, hierarchical microstructures, physical unclonable functions, titanium carbide TiCT MXene",

author = "Lin Jing and Qian Xie and Hongling Li and Kerui Li and Haitao Yang and Ng, {Patricia Li Ping} and Shuo Li and Yang Li and Teo, {Edwin Hang Tong} and Xiaonan Wang and Chen, {Po Yen}",

note = "Publisher Copyright: {\textcopyright} 2020 The Authors",

year = "2020",

month = dec,

day = "2",

doi = "10.1016/j.matt.2020.10.005",

language = "英语",

volume = "3",

pages = "2160--2180",

journal = "Matter",

issn = "2590-2393",

publisher = "Cell Press",

number = "6",

}

TY - JOUR

T1 - Multigenerational Crumpling of 2D Materials for Anticounterfeiting Patterns with Deep Learning Authentication

AU - Jing, Lin

AU - Xie, Qian

AU - Li, Hongling

AU - Li, Kerui

AU - Yang, Haitao

AU - Ng, Patricia Li Ping

AU - Li, Shuo

AU - Li, Yang

AU - Teo, Edwin Hang Tong

AU - Wang, Xiaonan

AU - Chen, Po Yen

PY - 2020/12/2

Y1 - 2020/12/2

N2 - Multigenerational 2D-material (2DM) microstructures are fabricated via sequential deformations in a transfer-free fashion and exhibit physical unclonable function patterns with algorithm-recognizable features. Deep learning (DL)-facilitated software is developed on the basis of the “classification and validation” mechanism to shorten the authentication time. With 2DM tags and DL software, a reliable and environmentally stable anticounterfeiting technology, DeepKey, is realized to show superior encoding capacity and fast authentication, which can be applied as an add-on covert layer for QR codes to provide two-layer information security.

AB - Multigenerational 2D-material (2DM) microstructures are fabricated via sequential deformations in a transfer-free fashion and exhibit physical unclonable function patterns with algorithm-recognizable features. Deep learning (DL)-facilitated software is developed on the basis of the “classification and validation” mechanism to shorten the authentication time. With 2DM tags and DL software, a reliable and environmentally stable anticounterfeiting technology, DeepKey, is realized to show superior encoding capacity and fast authentication, which can be applied as an add-on covert layer for QR codes to provide two-layer information security.

KW - MAP4: Demonstrate

KW - anticounterfeiting

KW - deep learning

KW - graphene oxide

KW - hierarchical microstructures

KW - physical unclonable functions

KW - titanium carbide TiCT MXene

UR - http://www.scopus.com/inward/record.url?scp=85097052725&partnerID=8YFLogxK

U2 - 10.1016/j.matt.2020.10.005

DO - 10.1016/j.matt.2020.10.005

M3 - 文章

AN - SCOPUS:85097052725

SN - 2590-2393

VL - 3

SP - 2160

EP - 2180

JO - Matter

JF - Matter

IS - 6

ER -

Multigenerational Crumpling of 2D Materials for Anticounterfeiting Patterns with Deep Learning Authentication

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this