Abstract:
Quick Response (QR) codes are extensively employed due to their compatibility with smartphone technology and the
technological advances of QR code scanners. With the ever-increasing adoption and utilization of QR codes in several real-life contexts,
finding effective and efficient security mechanisms to maintain their integrity has become crucial. Despite their popularity, QR codes
have been exploited as potential attack vectors through which attackers encode malicious URLs. Such attacks have become a critical
concern, necessitating effective countermeasures to mitigate them. This research paper proposes a dual machine learning-based model
called QR Shield. This QR shield aims to identify and detect the malicious links embedded in QR codes by utilizing a benchmark
dataset of URLs. The effectiveness of QR Shield was validated using four evaluation metrics, and experimental outcomes demonstrated
an accuracy rate of 96.8%. Based on these findings, the QR Shield exhibits a high potential to detect malicious QR codes, which
confirms the ability to generalize the proposed QR Shield to various real-life domains and applications. Additionally, the present
study contributes to the broader area of the QR code studies by offering comprehensive insight into the ability and potential of using
supervised machine learning models for QR code security and privacy.