Plasmonic Anticounterfeit Tags with High Encoding Capacity Rapidly Authenticated with Deep Machine Learning

Abstract

Counterfeit goods create significant economic losses and product failures in many industries. Here, we report a covert anticounterfeit platform where plasmonic nanoparticles (NPs) create physically unclonable functions (PUFs) with high encoding capacity. By allowing anisotropic Au NPs of different sizes to deposit randomly, a diversity of surfaces can be facilely tagged with NP deposits that serve as PUFs and are analyzed using optical microscopy. High encoding capacity is engineered into the tags by the sizes of the Au NPs, which provide a range of color responses, while their anisotropy provides sensitivity to light polarization. An estimated encoding capacity of 270 n is achieved, which is one of the highest reported to date. Authentication of the tags with deep machine learning allows for high accuracy and rapid matching of a tag to a specific product. Moreover, the tags contain descriptive metadata that is leveraged to match a tag to a specific lot number (i.e., a collection of tags created in the same manner from the same formulation of anisotropic Au NPs). Overall, integration of designer plasmonic NPs with deep machine learning methods can create a rapidly authenticated anticounterfeit platform with high encoding capacity.

Designer Plasmonic Nanostructures for Unclonable Anticounterfeit Tags

“…Shown in Figure 2c is a dark‐field microscopy image of a dilute deposition of gold nanorods (length 58 ± 5 nm, width 25 ± 2 nm), showing the potential to create random features from plasmonic nanoparticle deposits. [ 15 ]…”

“…Central to the creation of optical PUFs is achieving platforms with high ECs. [ 10,15 ] EC is the number of data points a data storage system can carry, which in the case of a PUF can be defined as the number of responses an image pixel can have ( R ) raised to the number of pixels ( n ) (EC = R n ). If the EC is too low, a PUF system can potentially be broken by trying all possible pattern combinations.…”

“…The underlying optical properties of metallic, semiconductor, and up‐converting nanomaterials are shown in Figure (top panels), along with examples of their use as anticounterfeit tags (bottom panels). [ 15–25 ] For example, semiconducting quantum dots show composition‐ and size‐dependent luminescence upon illumination by light of sufficient energy to promote electrons from their valance to conduction bands (Figure 1b, top), [ 26 ] whereas lanthanide‐doped nanoparticles can emit visible light through the process of up‐conversion in which two or more low energy photons are absorbed and emitted as one higher energy photon (Figure 1c, top). [ 27 ] Such emission can be used to create images and barcodes for security applications, as shown in Figure 1, bottom.…”

“…Adapted with permission. [ 15 ] Copyright 2021, American Chemical Society. b) From top to bottom: size‐dependent fluorescence from semiconductor nanocrystals where bandgap increases with decreasing size to tune the emission wavelength (Adapted with permission.…”

“…In contrast to fluorescent nanomaterials, plasmonic nanoparticles offer facile analysis by optical dark‐field scattering microscopy. A standout feature of plasmonic nanoparticles is their ability to maintain stable colors over time, [ 15 ] addressing the persistent challenges of photobleaching, insufficient fluorescence intensity, and short‐lived fluorescence encountered with luminescent nanoparticles and PUFs. [ 35 ] Plasmonic nanomaterials have been used to create security images and barcodes, often in combination with Raman imaging when their surfaces have been modified with appropriate reporter molecules, as shown in Figure 1a.…”