MAster assignment
Development of a Real-Time Quishing Detection Tool Using Hybrid Machine Learning Approaches: Integrating Structural and URL-Based Analysis
Type: Master CS
Period: Start date: as soon as possible
Student: Unassigned
If you are interested please contact:
Abstract:
Problem Statement: Quishing attacks, where malicious QR codes lead users to phishing sites, represent a growing cybersecurity threat, particularly in mobile transactions and payments. Current solutions primarily focus on URL-based detection, neglecting structural anomalies within the QR codes themselves. This research introduces a comprehensive detection framework that combines both structural and URL-based anomaly detection, leveraging machine learning models to offer a more robust defense against Quishing attacks. The key features of the research are Structural and URL analysis, Threat Intelligence Integration, Cross-Platform Implementation including Android and browser extension, and Scalability testing to ensure its scalability, robustness, and practical use. The outcome will be a comprehensive, real-time Quishing detection tool that effectively prevents malicious QR code attacks by combining structural and URL anomaly detection, with the ability to learn and adapt to emerging threats.
References:
- Amoah, G. A., & Hayfron-Acquah, J. B. (2022). QR Code Security: mitigating the issue of Quishing (QR Code Phishing). International journal of computer applications, 184(33), 34-39.
- William, F. (2024). Machine learning, Fuzzy logic, and Zero Trust-Based Quishing Prevention solution for Android Smartphones.
- Bekavac, L. J. L., Mayer, S., & Strecker, J. (2024, May). QR-Code Integrity by Design. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (pp. 1-9).