Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index; none of the 33 sources its claims cite is checked for support yet.

Modular Anti‐Counterfeit Tags Formed by Template‐Assisted Self‐Assembly of Plasmonic Nanocrystals and Authenticated by Machine Learning

Open access
Ibrar, Maha, Huang, Sheng‐Yuan, McCurtain, Zachery, Naha, Shujon, Crandall, David J., Jacobson, Stephen C., Skrabalak, Sara E. · 2024 · Advanced Functional Materials

Abstract

Counterfeit goods are pervasive, being found in products as diverse as textiles and optical media to pharmaceuticals and sensitive electronics. Here, an anti‐counterfeit platform is reported in which plasmonic nanoparticles (NPs) are used to create unique image tags that can be authenticated quickly and reliably. Specifically, plasmonic NPs are assembled into periodic arrays of NP clusters by template‐assisted self‐assembly (TASA), where the light scattering responses from the arrays are analyzed by dark‐field optical microscopy. Tag design proved modular as plasmonic NPs with different optical responses can be selected and paired with Templates with different features (e.g., well size, well shape, and number and arrangement of wells in an array), giving access to a variety of color responses and unique images. These images can be differentiated from one another and authenticated by image analysis. Authentication methods based on shallow and deep neural networks are compared, where deep neural networks authenticated TASA tags with higher accuracy. Given the ease of tag fabrication and rapid image analysis, these platforms are ideal for on‐the‐fly tagging and supply‐chain authentication of critical goods.

Overview

CoChat Summary

TL;DR

Template-assisted self-assembly of plasmonic Au nanocrystals into periodic arrays creates modular anti-counterfeit tags whose dark-field scattering images are authenticated by machine learning. A deep neural network (ViT + SVM) classified template categories with 89% accuracy, outperforming a shallow neural network (51%) for template classification while both achieved 71% for ink classification.

Key findings

  • Plasmonic Au NP inks and patterned templates gave modular optical tags: Ink A nanorods had length 67.3 ± 7.7 nm, width 19.2 ± 2.3 nm, aspect ratio 3.5, LSPRL at 695 nm; Ink B nanorods had length 91.2 ± 10.1 nm, width 38.2 ± 4.2 nm, aspect ratio 2.4, LSPRL at 625 nm; Ink C quasi-spherical NPs had diameter 68.8 ± 7.1 nm and a dipolar resonance at 525 nm.
  • Template features changed tag color and brightness: Template I with Ink A gave an average brightness of 93.7 au versus 36.1 au for Template V with Ink A; Ink B with Template IV gave 95.5 au versus 73.6 au for Template I.
  • Shallow neural network (Method 1) classified inks with overall accuracy 71%: Ink A 84%, Ink B 51%, Ink C 79%; template categorization accuracy was 51%.
  • Deep neural network (Method 2, ViT + SVM) classified inks with overall accuracy 71%: Ink A 80%, Ink B 52%, Ink C 82%; template classification improved to 89%, with Template I 100%, Template II 78%, Template III 100%, Template IV 89%, and Template V 61%.

Methods

  • Tags were fabricated by template-assisted self-assembly (TASA): PEGylated Au NP inks were drop-cast onto x-PDMS/PDMS templates, a hydrophilized glass substrate was lowered onto the template, dried for 12 h, and lifted off to transfer the NP array.
  • Dark-field optical microscopy with a color CCD camera imaged the scattering response at 100× magnification, 1 s acquisition, ISO 200; a blob detection algorithm extracted RGB values, array size, and well spacing while excluding artifacts.
  • Authentication compared Method 1, a five-layer shallow neural network trained in TensorFlow on extracted RGB features with an 80/20 train/test split and confusion matrices averaged over ten trials, against Method 2, a pretrained ViT-Huge feature extractor with a linear SVM classifier.

Limitations

  • The paper states that manual TASA limits the number of tags generated, human handling can affect NP assembly quality, and a larger dataset is needed to improve neural network robustness; it also notes that diffuse reflectance spectroscopy showed limited features for these tags and that a full techno-economic analysis was not undertaken.
  • The paper states Method 1 is limited to select tag designs, and blob detection had difficulty extracting cell numbers accurately for Templates IV and V because of their larger array and cluster spacings.
  • Evident from the reported confusion matrices: Ink B classification was low for both methods (51% and 52%), and Template V classification by the deep model was 61%, indicating that some Ink-Template combinations remain harder to authenticate reliably.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1002/adfm.202400842

Cites

60 of 60 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1. Scheme for tag fabrication that involves four steps. First is selection and synthesis of plasmonic NP Inks and design of Templates and their replication. Second, Inks are drop-cast onto Templates for TASA. Third, the pattern is transferred onto a substrate through lift-off. Finally, the scattering response through a dark-field optical microscope is captured by an interfaced CCD camera.
Figure 1. Scheme for tag fabrication that involves four steps. First is selection and synthesis of plasmonic NP Inks and design of Templates and their replication. Second, Inks are drop-cast onto Templates for TASA. Third, the pattern is transferred onto a substrate through lift-off. Finally, the scattering response through a dark-field optical microscope is captured by an interfaced CCD camera.CC BY-NC-ND · PubMed Central
Figure 2. a) TEM images for Au NP Inks A, B, and C, with cartoon models of the NPs used as reference in future images. b) Schematic representations of Templates I–V where W is the well width, D is the well depth, L is the spacing between wells, and A is the array size.
Figure 2. a) TEM images for Au NP Inks A, B, and C, with cartoon models of the NPs used as reference in future images. b) Schematic representations of Templates I–V where W is the well width, D is the well depth, L is the spacing between wells, and A is the array size.CC BY-NC-ND · PubMed Central
Figure 3. This figure is organized as a grid where the top row shows schematics of the five Templates described in Figure 2. The second row shows dark-field images from the TASA of Ink A with Templates I–V. Below are the corresponding SEM images for the TASA of Ink A with Templates I–V. Similarly, the fourth and fifth rows show dark-field images and SEM images, respectively, from TASA of Ink B with Templates I–V. The sixth and the seventh rows show dark-field and SEM images, respectively, from TASA of Ink C from Templates I–V. The scale bar on the top is for all the dark-field images. Scale bars at the bottom are for (left) SEM images from Templates I–IV and (right) for all SEM images in column V from Template V.
Figure 3. This figure is organized as a grid where the top row shows schematics of the five Templates described in Figure 2. The second row shows dark-field images from the TASA of Ink A with Templates I–V. Below are the corresponding SEM images for the TASA of Ink A with Templates I–V. Similarly, the fourth and fifth rows show dark-field images and SEM images, respectively, from TASA of Ink B with Templates I–V. The sixth and the seventh rows show dark-field and SEM images, respectively, from TASA of Ink C from Templates I–V. The scale bar on the top is for all the dark-field images. Scale bars at the bottom are for (left) SEM images from Templates I–IV and (right) for all SEM images in column V from Template V.CC BY-NC-ND · PubMed Central
Figure 4. a) Data extraction: An optical image of a tag is collected, and a blob detection algorithm is used to identify clusters and extract RGB values from each cluster in addition to array size (A), average well width (W), average well spacing (L), and number of cells for an array. B) Reproducibility study: Top Row) From left to right, dark-field optical microscopy images from 5 different tags created by the deposition of Ink A with Template III. Scale bar represents 2 μm. Middle Row) RGB histograms arising from the corresponding tags above, where the bin height corresponds to the primary color intensity for a particular intensity range normalized to the total counts of blobs detected by the algorithm. The bin width of the histograms is 18. These histograms show the RGB color contribution and distribution in the detected blobs for each tag. Normal distributions group the R, G, and B intensity histograms. Bottom Row) 3-D scatter plots of the RGB responses from blob detection analysis of the corresponding tag above.
Figure 4. a) Data extraction: An optical image of a tag is collected, and a blob detection algorithm is used to identify clusters and extract RGB values from each cluster in addition to array size (A), average well width (W), average well spacing (L), and number of cells for an array. B) Reproducibility study: Top Row) From left to right, dark-field optical microscopy images from 5 different tags created by the deposition of Ink A with Template III. Scale bar represents 2 μm. Middle Row) RGB histograms arising from the corresponding tags above, where the bin height corresponds to the primary color intensity for a particular intensity range normalized to the total counts of blobs detected by the algorithm. The bin width of the histograms is 18. These histograms show the RGB color contribution and distribution in the detected blobs for each tag. Normal distributions group the R, G, and B intensity histograms. Bottom Row) 3-D scatter plots of the RGB responses from blob detection analysis of the corresponding tag above.CC BY-NC-ND · PubMed Central
Figure 5. a) Left: Schematic of Template I and dark-field image from the tag created with Ink A and Template I. Middle: Corresponding RGB histogram. Right: Corresponding 3-D scatter plot of RGB responses. b) Left: Schematic of Template II and dark-field image from tag created with Ink A and Template II. Middle: Corresponding RGB histogram. Right: Corresponding 3-D scatter plot of RGB responses. c) Left: Schematic of Template II and dark-field image from tag created with Ink B and Template II. Middle: Corresponding RGB histogram. Right: Corresponding 3-D scatter plot of RGB responses.
Figure 5. a) Left: Schematic of Template I and dark-field image from the tag created with Ink A and Template I. Middle: Corresponding RGB histogram. Right: Corresponding 3-D scatter plot of RGB responses. b) Left: Schematic of Template II and dark-field image from tag created with Ink A and Template II. Middle: Corresponding RGB histogram. Right: Corresponding 3-D scatter plot of RGB responses. c) Left: Schematic of Template II and dark-field image from tag created with Ink B and Template II. Middle: Corresponding RGB histogram. Right: Corresponding 3-D scatter plot of RGB responses.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

0 Valid · 1 Not valid · 21 Not checked · 116 Own results and interpretations

68 more claims

Create a free account to see all 138 claims and to verify the 3 references still open.

See all claims — free account
  • The quote only partly states this claim. 10
  • It may state two separate claims as one. 31
  • Probably not a substantial claim. 28

Create a free account to see these claims.

Citations

Cites

Show all 60 references

Cited by

See all 19

Metadata

Authors
Ibrar, M., Huang, S., McCurtain, Z., Naha, S., Crandall, D. J., Jacobson, S. C., & Skrabalak, S. E.
Affiliations
Indiana University Bloomington (US)
Corresponding author
Skrabalak, Sara E.
Venue
Advanced Functional Materials
Publisher
Wiley
Published
2024-07-10
Volume
34
Issue
41
ISSN
  • 1616-301X (ISSN-L)
  • 1616-3028
OpenAlex
W4400508005
Cited by
19
References
60
Citations by year
2026: 6 · 2025: 12 · 2024: 1
FWCI
1.45
Type
journal article
Language
en
Open access
Locations
  • Advanced Functional Materials (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion, cc-by-nc-nd)
Funders
  • Research Corporation for Science Advancement (FRED Award)
  • NIH Office of the Director (R35 GM141922)
  • Arkansas NSF EPSCoR (CHE‐0923064)
  • Indiana University
Topics
  • Physical Sciences › Materials Science › Electronic, Optical and Magnetic Materials › Gold and Silver Nanoparticles Synthesis and Applications
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Plasmonic and Surface Plasmon Research
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Photonic Crystals and Applications
Keywords
plasmonic nanoparticles, template-assisted self-assembly, nanoparticle clusters, light scattering, dark-field microscopy, image tags, deep neural network, counterfeit goods

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-11-19, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-11-19 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Modular Anti‐Counterfeit Tags Formed by Template‐Assisted Self‐Assembly of Plasmonic Nanocrystals and Authenticated by Machine Learning. https://app.cochat.ai/papers/10.1002/adfm.202400842
The paper
Ibrar, M., Huang, S., McCurtain, Z., Naha, S., Crandall, D. J., Jacobson, S. C., & Skrabalak, S. E. (2024). Modular Anti‐Counterfeit Tags Formed by Template‐Assisted Self‐Assembly of Plasmonic Nanocrystals and Authenticated by Machine Learning. Advanced Functional Materials. https://doi.org/10.1002/adfm.202400842

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.