Enhancing secure QR code steganography through artificial intelligence: a conceptual framework

The incorporation of modern barcode decoding technology into smartphones allows for the extraction of data contained inside QR codes. The use of QR codes for transmitting confidential information, such as e-tickets, discounts, and other sensitive data, raises worries about potential security risks. It is imperative to employ resilient QR code algorithms to guarantee the security of QR code applications in response to this challenge. This study presents a method for achieving product authentication through data concealing. The strategy involves using user data to generate a QR (Quick Response) code, which is then embedded into the product logo picture. The embedded QR code is not visible to the human eye. QR codes are renowned for their robust error-correcting system and excel in concealing random information. Convolutional neural networks (CNN) are a type of deep neural networks that enable the analysis of visual images and the recognition of patterns. The aim of this article is to employ the CNN method to conceal a QR code within the logo picture of a user's products. The suggested model consists of two Convolutional Neural Networks (CNNs), namely an encoder CNN and a decoder CNN. The role of the encoder Convolutional Neural Network (CNN) is to integrate the QR code into the user's product logo picture and produce an output image that closely resembles the original user image. The job of the decoder convolutional neural network (CNN) is to take the output of the encoder CNN as input and produce the embedded QR code picture as output. Our technique incorporates advanced security measures and conceals sensitive information, thereby preventing the unauthorized replication and misuse of the QR code.

Text 117679.pdf - Published Version Available under License Creative Commons Attribution Non-commercial. Download (2MB) Official URL or Download Paper: https://semarakilmu.com.my/journals/index.php/appl...

Actions (login required)

View Item