Informations

Stand number

J126

Exhibition class

W: Hardware – Software – Cybersecurity – Blockchain – Internet of things (IoT)

Technical description

A privacy-preserving QR code authentication method using Vision Transformer-based Federated Learning. It enhances security by decentralizing data and improves accuracy on blurred codes with a Cyclic Weight Transfer strategy.

Simplified description

This new technology boosts QR code security using an innovative system that combines privacy protection with better accuracy. It uses a method called Federated Learning to keep data decentralized and private, while a unique strategy helps accurately read even blurry QR codes.