Matter
Volume 3, Issue 6, 2 December 2020, Pages 2160-2180
Journal home page for Matter

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

https://doi.org/10.1016/j.matt.2020.10.005Get rights and content
Under a Creative Commons license
open access

Highlights

  • Multiscale 2D-material microstructures are fabricated via sequential deformations

  • Multigenerational 2D-material microstructures serve as PUF key-based patterns

  • DL-facilitated software is developed to accelerate authentication

  • DeepKey anticounterfeiting features high encoding capacity and fast authentication

Progress and Potential

Physical unclonable function (PUF) is a cornerstone of anticounterfeiting, yet conventional PUF key-based tags encounter several bottlenecks, such as complicated manufacturing, specialized and tedious readout, long authentication time, and insufficient environmental stability. Here, we utilize two-dimensional materials (2DMs) to construct multigenerational microstructures as PUF patterns. By implementing two in situ treatments during sequential substrate contractions, multigenerational 2DM PUF patterns are produced in a transfer-free and scalable fashion. A deep learning (DL)-facilitated authentication software is further developed on the basis of the “classification and validation” mechanism, shortening the authentication time significantly. The synergy between 2DM tags and DL authentication software enables a DeepKey anticounterfeiting technology with superior encoding capacity and fast authentication, which can be integrated with QR codes to provide two-layer information security.

Summary

Physical unclonable function (PUF) is a cornerstone of anticounterfeiting. However, conventional PUF key-based secure tags encounter several bottlenecks, such as complicated manufacturing, specialized and tedious readout, long authentication time, and insufficient stability. Here, we utilize various two-dimensional materials (2DMs), including Ti3C2Tx MXene and graphene oxide, to construct multigenerational microstructures as PUF patterns. Two intermediate treatments, cation intercalation and moisture-induced lubrication, are introduced in between sequential contractions to engineer the multiscale patterns in a transfer-free and scalable fashion. A deep learning (DL)-facilitated software is developed to pre-categorize the hierarchical topographies with classifiable features. Thereafter, the search-and-compare is conducted within a smaller database to shorten the overall authentication time. The synergy between 2DM tags and DL-facilitated software enables a reliable and environmentally stable anticounterfeiting technology, DeepKey, showing superior encoding capacity (>10144,494) and short authentication time (∼3.5 min). Our 2DM anticounterfeiting tag is finally integrated with QR codes to provide two-layer information security.

Material Advancement Progression

MAP4: Demonstrate

Keywords

hierarchical microstructures
titanium carbide Ti3C2Tx MXene
graphene oxide
physical unclonable functions
anticounterfeiting
deep learning

Cited by (0)

4

These authors contributed equally

5

Lead Contact