QR Code Malicious URL Detection System Using Machine Learning

The rapid rise of QR Codes in payments, advertising, and authentication has introduced significant cybersecurity risks, as attackers increasingly embed malicious URLs to
compromise devices and steal sensitive information. To address this challenge, this project proposes a QR Code Malicious URL Detection System leveraging advanced machine
learning models for improved accuracy and adaptability.
Four algorithms are employed: Passive-Aggressive Algorithm, Quadratic Discriminant Analysis (QDA), Ridge Classifier, and Extra Trees Classifier, which can operate individually or in combination to enhance detection performance. By integrating QR Code�specific analysis with robust machine learning techniques, the system can effectively identify potentially harmful URLs, providing a scalable, adaptive, and reliable solution for modern cybersecurity threats. This framework ensures proactive detection of malicious QR codes, safeguarding users from evolving digital threats and reinforcing trust in QR-based applications.