Prevention of Attacks Using QR Codes Based on Cryptographic Approaches and Machine Learning Methods

QR codes have become a ubiquitous tool in modern society, widely used in mobile payments, authentication, marketing, and e-government services; however, their increasing adoption has also introduced new security challenges, as attackers exploit QR codes to distribute malicious software, conduct phishing attacks (QRishing), and steal sensitive user data. Since the first reported malicious QR code attack in 2011, the number and sophistication of such threats have steadily grown, particularly targeting smartphones and other mobile devices. Existing protection mechanisms, including URL verification tools, visual markers, and traditional cryptographic methods, often fail to provide a comprehensive and scalable solution, making advanced defense strategies essential. This paper provides a systematic overview of current QR code security threats and countermeasures, with a particular focus on cryptographic approaches and machine learning-based detection methods, while critically analyzing the limitations of existing solutions. Furthermore, we propose a secure architectural framework that integrates modern cryptographic algorithms with intelligent threat detection to achieve a balance between security, performance, and usability, thereby enhancing the resilience of QR codes against emerging attacks. Our findings contribute to the ongoing discussion on mobile security and highlight the necessity of robust, scalable mechanisms for protecting future applications.

Ҳали таржима қилинмаган