As a result of simplicity of use and convenience, QR codes are now frequently utilized for digital payments, authentication, and information exchange. However, because of their increasing popularity, they are now a target for nefarious operations including data theft, phishing, and redirection to dangerous websites. Real-time detection of such threats is frequently beyond the capabilities of traditional security procedures. In order to secure QR code infrastructure, this article proposes an AI-based solution that uses machine learning techniques to identify fraudulent activities. Based on predetermined and learned patterns, the system examines the content of QR codes, extracts embedded data, including URLs, and assesses possible dangers. To enable customers to scan or upload QR codes and obtain immediate security evaluations, a Django-based web application is created. The technology successfully and accurately detects malicious QR codes, according to experimental data. The suggested solution offers a scalable approach to QR code security, increases user safety, and boosts confidence in QR-based solutions.
Ekambaram et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: