Random Fractal-enabled Physical Unclonable Functions with Dynamic AI Authentication
Overview
Affiliations
A physical unclonable function (PUF) is a foundation of anti-counterfeiting processes due to its inherent uniqueness. However, the self-limitation of conventional graphical/spectral PUFs in materials often makes it difficult to have both high code flexibility and high environmental stability in practice. In this study, we propose a universal, fractal-guided film annealing strategy to realize the random Au network-based PUFs that can be designed on demand in complexity, enabling the tags' intrinsic uniqueness and stability. A dynamic deep learning-based authentication system with an expandable database is built to identify and trace the PUFs, achieving an efficient and reliable authentication with 0% "false positives". Based on the roughening-enabled plasmonic network platform, Raman-based chemical encoding is conceptionally demonstrated, showing the potential for improvements in security. The configurable tags in mass production can serve as competitive PUF carriers for high-level anti-counterfeiting and data encryption.
Nanoscale Silicon Fingerprints for Counterfeit Prevention in Microchips.
Liu B, Farhadi A, Bartschmid T, Zhang Y, Guo C, Feng S Small. 2025; 21(10):e2500878.
PMID: 39905893 PMC: 11899515. DOI: 10.1002/smll.202500878.
Zhang J, Creamer A, Xie K, Tang J, Salter L, Wojciechowski J Nat Commun. 2025; 16(1):502.
PMID: 39779668 PMC: 11711641. DOI: 10.1038/s41467-024-55646-4.
Ruzi M, Celik N, Sahin F, Sakir M, Onses M Small. 2025; 21(6):e2408189.
PMID: 39757431 PMC: 11817952. DOI: 10.1002/smll.202408189.
Murataj I, Magosso C, Carignano S, Fretto M, Ferrarese Lupi F, Milano G Nat Commun. 2024; 15(1):10576.
PMID: 39663369 PMC: 11634899. DOI: 10.1038/s41467-024-54492-8.
High-dimensional anticounterfeiting nanodiamonds authenticated with deep metric learning.
Wang L, Yu X, Zhang T, Hou Y, Lei D, Qi X Nat Commun. 2024; 15(1):10602.
PMID: 39638812 PMC: 11621400. DOI: 10.1038/s41467-024-55014-2.