An application that significantly improves the traceability of the manufacturing sector and agriculture is the two-dimensional barcode (QR code). The QR code, however, is simple to copy and fake. Therefore, we suggest a novel strategy to prevent tampering with this code. The method entails two stages: concealing a security element in the QR code, and assessing how closely the QR code on the goods resembles genuine ones. For the first problem, error-correcting coding is used to encode and decode the secret feature in order to manage faults in noisy communication channels. A deep neural network is used to both conceal and decode the encoded data in the QR code. The suggested network has the ability to be resilient to actual distortions brought on by the printing and photographing processes. For the latter problem, we measure the similarity of QR codes using the Siamese network design. To assess if a QR code is real or false, the extracted secret feature and the outcome of the QR code similarity estimation are merged. With an average accuracy of 98%, the suggested method performs well and may be used to validate QR codes in practical applications.