US 2026/0288985 A1Published application

System and method for privacy-preserving printer source identification of qr code labels

AssigneeLingnan University

InventorsSam Tak Wu KWONG, Zhongyuan GUO

Life of this patent

Estimating the term…

Loading patent…

Abstract

In the present invention, federated learning provides a solution by enabling models to be trained using locally distributed data across multiple clients, reducing reliance on a centralized server. Each client, such as each smartphone in a smartphone group, independently trains a local model using its dataset and shares only model parameters with other participants, without transmitting actual QR code image data. The decentralized learning approach enhances data security and privacy, as sensitive information remains on-device, mitigating risks associated with data leakage and unauthorized access. Furthermore, by leveraging cyclic weight transfer, the system allows smartphones to sequentially update model weights, contributing to a continuously improving global model while preserving user privacy.

Claims20

Dependent claims

A system for printer source identification through classifying QR codes, comprising:

at least one data collection module configured to acquire QR code images from different printers which comprise both legitimate and counterfeit devices to construct a QR code dataset;
at least one data preprocessing module communicating with the data collection module and configured to extract QR code regions from the QR code images of the QR code dataset, convert the extracted QR code regions into fixed-size patches, and apply position embeddings to format the patches for transformer-based analysis;
a pre-trained model storage and retrieval module configured to store a vision transformer(ViT) model pre-trained on a large-scale dataset and to retrieve the pre-trained ViT model when required for QR code printer source identification;
a fine-tuning module communicating with the data preprocessing module and the pre-trained model storage and retrieval module and configured to adapt the pre-trained ViT model to the QR code printer source identification by optimizing the pre-trained ViT model for printer-specific feature extraction and classification;
a QR code source identification module configured to classify QR codes based on their source printers by utilizing the fine-tuned ViT model and to generate corresponding classification results;
a decentralized learning module configured to facilitate local updates of the ViT model on smartphones performing the QR code printer source identification, wherein only model parameters are transmitted to prevent raw data transmission to a central server;
a cyclic weight transfer module configured to sequentially transmit updated model weights of the ViT model across the smartphones, allowing each of the smartphones to preserve user privacy and avoid centralized raw data aggregation;
and
a verification and output module communicating with the QR code source identification module and configured to determine whether one or more given QR codes originate from an authorized printer and to output one or more verification results indicating authenticity or counterfeit status.

6 more elements

A method for printer source identification through classifying QR codes, comprising:

acquiring, by at least one data collection module, QR code images from different printers which comprise both legitimate and counterfeit devices to construct a QR code dataset;
extracting, by at least one data preprocessing module, QR code regions from the QR code images of the QR code dataset;
converting, by the data preprocessing module, the extracted QR code regions into fixed-size patches;
applying, by the data preprocessing module, position embeddings to format the patches for transformer-based analysis;
storing, by a pre-trained model storage and retrieval module, a vision transformer(ViT) model pre-trained on a large-scale dataset;
retrieving, by the pre-trained model storage and retrieval module, the pre-trained ViT model when required for QR code printer source identification;
adapting, by a fine-tuning module, the pre-trained ViT model to the QR code printer source identification by optimizing the pre-trained ViT model for printer-specific feature extraction and classification;
classifying QR codes, by QR code source identification module, based on their source printers by utilizing the fine-tuned ViT model and thus generating corresponding classification results;
facilitating, by a decentralized learning module, local updates of the VIT model on smartphones performing the QR code printer source identification, wherein only model parameters are transmitted to prevent raw data transmission to a central server;
sequentially transmitting, by a cyclic weight transfer module, updated model weights of the ViT model across the smartphones, thereby allowing each of the smartphones to preserve user privacy and avoid centralized raw data aggregation;
and
determining, by a verification and output module, whether one or more given QR codes originate from an authorized printer and thus outputting one or more verification results for indicating authenticity or counterfeit status.

9 more elements

Dependencies are inferred from the claim text.