QR Code Attack Detection for Mobile Security

This research project has successfully engineered, implemented, and validated a lightweight, highly responsive, real-time QR Code Attack Detection System specifically designed to reinforce client-side mobile security configurations against modern social engineering threats. By shifting the primary analytical defensive mechanisms from conventional, slow cloud-dependent lookup databases directly to an optimized on-device heuristic evaluation script layer, the developed platform completely eliminates network routing overheads, multi-hop lookup delays, and data transmission latency bottlenecks. This ensures that defensive profiling occurs instantly upon data acquisition, making it exceptionally well-suited for deployment on consumer-grade mobile devices with limited hardware resources.   The successful integration of the custom 5-rule heuristic checking engine allows the application to accurately categorize multi-vector QR code inputs into structured, color-coded risk profiles—Green (Safe), Orange (Suspicious), and Red (Malicious)—prior to browser interaction. This proactive interception pipeline fundamentally halts the execution of hidden zero-day quishing links, automated drive-by malware downloads, and manipulative web redirection pathways. Furthermore, the platform achieves robust operational sustainability by preserving detailed historical records within a local SQLite database infrastructure, which seamlessly feeds an interactive administrative dashboard equipped with responsive data tracking charts and configuration panels.   Ultimately, this project demonstrates that robust, modern anti-phishing defense mechanisms can be deployed natively within mobile client environments without compromising processing efficiency or user convenience. The resulting application provides an accessible, reliable, and user-centric security framework that effectively hardens mobile devices against the rapidly growing threat of QR-code-based cyberattacks.

1.             Ahmad  Sahban Rafsanjani , Norshaliza  B .Kamaruddin(2023). QSecR:Secure QR code scanner According to a novel malicious URL detection framework, IEEE Access :https://ieeexplore.ieee.org/document/10172018.   2.      Aayush Trivedi, Krishnappa Jangal, Rashi Gupta(2025) Phishing Detection in Advanced QR Code Attacks: Challenges and AI- Driven Solutions, International Journal for Research in Applied Science & Engineering Technology(URASET) :https://www.ijraset.com/research-paper/phishing-detection- in-advanced-qr-code-attacks. 3.       Rouwa Yalda, Arshad Khan, Narayan Nepal(2026).B-PhishQR – A BlockChain- based framework for secure QR code   Verification   against   Phishing attacks :https://www.sciencedirect.com/science/article/pii/S277250 3025001033. 4.    Irving Barron, Gaurav Sharma (2025). Quashing Quishing Attacks Using Self- Authenticating Dual-Modulated QR Codes, IEEE Security & Privacy. DOI: https://ieeexplore.ieee.org/document/10877412   5.          Muhammad Wahid Akram, Keshav Sood, Muneeb Ul Hassan (2025). QRïS: A Preemptive Novel Method for Quishing Detection Through Structural Features of QR Codes, arXiv : https://arxiv.org/abs/2510.17175   6.     Jikesh Thapa, Gurrehmat Chahal, Șerban Voinea Gabreanu, Yazan Otoum (2025). Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models, arXiv : https://arxiv.org/abs/2507.07406 Saranya Vaithilingam, Santhosh Aradhya Mohan Shankar (2024). Enhancing Security in QR Code Technology Using AI: Exploration and Mitigation Strategies, International Journal of Intelligence Science https://doi.org/10.4236/ijis.2024.142003