International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

UPI Scam Detection for QR Codes

Himanshu TriguneStudent, Computer Engineering Diploma, Ajeenkya D. Y. Patil School of Engineering, Charholi, Pune, IndiaSumit PawarStudent, Computer Engineering Diploma, Ajeenkya D. Y. Patil School of Engineering, Charholi, Pune, IndiaPranit ChavanStudent, Computer Engineering Diploma, Ajeenkya D. Y. Patil School of Engineering, Charholi, Pune, IndiaSushant TatpalleStudent, Computer Engineering Diploma, Ajeenkya D. Y. Patil School of Engineering, Charholi, Pune, IndiaProf. Priya BorkarGuide, Professor, Computer Engineering Diploma, Ajeenkya D. Y. Patil School of Engineering, Charholi, Pune, IndiaProf. Nita PawarHoD, Professor, Computer Engineering Diploma, Ajeenkya D. Y. Patil School of Engineering, Charholi, Pune, India

Vol 9 No 12 (2025): Volume 9, Issue 12, December 2025 | Pages: 98-104

International Research Journal of Innovations in Engineering and Technology

OPEN ACCESS | Research Article | Published Date: 20-12-2025

doi Logo doi.org/10.47001/IRJIET/2025.912014

pdf iconFull Text PDF
Abstract

The proposed UPI Scam Detection System for QR Codes is designed to protect users from fraudulent digital payment activities by automatically analyzing, verifying, and validating QR codes before any transaction takes place. With increasing dependence on UPI-based payments in India, scamsters exploit users by generating malicious QR codes that redirect payments to unauthorized accounts. Traditional QR scanners lack fraud-detection intelligence and operate purely as decoding tools.

This project introduces an intelligent, web-based fraud prevention system that integrates Django, computer vision, and machine learning to detect manipulated QR codes, cloned merchant IDs, suspicious patterns, tampered images, and mismatched UPI handles. The system uses an image-based ML classifier trained on genuine and fraudulent QR datasets to flag anomalies, while server-side validation checks UPI patterns, metadata integrity, and image distortion parameters. A user-friendly web dashboard allows scanning, verification, reporting, and visualization of risk levels.

The solution enhances digital payment safety by identifying scam indicators in real-time, empowering users and businesses to validate QR codes prior to transactions. The system also establishes a scalable framework for future integration with mobile apps, OCR-based metadata extraction, and real-time fraud databases.

Keywords

UPI Scam Detection, QR Code Security, Django, Image Processing, Machine Learning, Payment Fraud Prevention, Deep Learning, Phishing Prevention, Computer Vision


Citation of this Article

Himanshu Trigune, Sumit Pawar, Pranit Chavan, Sushant Tatpalle, Prof. Priya Borkar, & Prof. Nita Pawar. (2025). UPI Scam Detection for QR Codes. International Research Journal of Innovations in Engineering and Technology - IRJIET, 9(12), 99-104. Article DOI https://doi.org/10.47001/IRJIET/2025.912014

Licence Copyright (c) 2026 International Research Journal of Innovations in Engineering and Technology creative common licence This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
References
  1. R. Sharma and P. Jain, “A Study on QR Code–Based Fraud in Digital Payment Systems,” International Journal of Computer Science and Information Security, vol. 19, no. 6, pp. 45–52, 2021.
  2. A.Patel, “Image Tampering Detection Using Machine Learning Techniques,” IEEE Transactions on Information Forensics and Security, vol. 15, no. 4, pp. 1123–1134, 2020.
  3. S. Kumar and V. Rao, “Security Analysis of QR Code Payments in Unified Payment Interface (UPI),” International Journal of Cyber Security and Digital Forensics, vol. 11, no. 2, pp. 78–86, 2022.
  4. J. Smith and L. Johnson, “Detection of Visual Manipulation in QR Codes Using Computer Vision,” Journal of Digital Image Processing, vol. 14, no. 3, pp. 201–210, 2020.
  5. S. Vincent, “Machine Learning Integration in Django-Based Web Applications,” Proceedings of the International Conference on Applied Computation and Security, pp. 78–84, 2021.
  6. National Payments Corporation of India (NPCI), “Unified Payments Interface (UPI) – Procedural Guidelines and Safety Measures,” NPCI White Paper, Mumbai, India, 2023.
  7. M. Gupta and R. Verma, “QR Code Phishing Attacks: Threats and Countermeasures,” International Journal of Network Security, vol. 24, no. 1, pp. 15–23, 2022.
  8. T. Nguyen and H. Lee, “Machine Learning-Based Fraud Detection in Digital Payment Systems,” IEEE Access, vol. 9, pp. 134567–134579, 2021.
  9. OpenCV Documentation, “Computer Vision Techniques for Image Analysis and QR Code Processing,” OpenCV Foundation, 2024. Available: https://opencv.org
  10. Django Software Foundation, “Django Documentation – Secure Web Application Development,” Version 4.x, 2024. Available: https://www.djangoproject.com
  11. S. Chandrasekaran and M. Kumar, “Digital Payment Security in Emerging Economies,” Journal of Information Security and Applications, vol. 64, pp. 102–110, 2022.
  12. A.Mehta and N. Shah, “Anomaly Detection in Digital Images Using Support Vector Machines,” International Journal of Advanced Research in Engineering and Technology, vol. 10, no. 5, pp. 389–397, 2019.

Copyright @ 2026 IRJIET. All Right Reserved.

Licensed underCreative Commons Attribution 4.0 International License.