AI-Based UPI Scam Detection and Reporting System Using Crowdsourced Patterns & Verified Reports

  • Unique Paper ID: 183933
  • PageNo: 3762-3765
  • Abstract:
  • The rapid adoption of digital payment platforms such as Unified Payments Interface (UPI) has revolutionized financial transactions by offering speed, convenience, and accessibility. However, this growth has also led to a surge in fraudulent activities, where unsuspecting users fall victim to scams involving fake UPI IDs, QR codes, and malicious requests. To address this challenge, we propose an AI-enabled UPI Scam Detection and Reporting System that leverages machine learning and crowd-sourced intelligence to detect and prevent fraudulent transactions in real-time. The system analyses UPI ID patterns, transaction frequency, user engagement behaviour, and historical interactions to assign a dynamic scam likelihood score to unknown or suspicious UPI IDs. Based on this score, users receive instant alerts prior to initiating payments, thereby reducing the risk of financial loss. Furthermore, the framework integrates a reporting mechanism where users can flag suspicious UPI IDs and QR codes, which are then verified and incorporated into the fraud detection model to enhance accuracy over time. By combining behavioural analysis with community-driven reporting, the proposed solution strengthens the security of digital transactions and supports payment platforms such as Google Pay, PhonePe, and Paytm in combating fraud. This system aims to create a safer and more reliable digital payment ecosystem while empowering users with proactive scam prevention tools.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{183933,
        author = {DASARI JHANSI LAKSHMI},
        title = {AI-Based UPI Scam Detection and Reporting System Using Crowdsourced Patterns & Verified Reports},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {3762-3765},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183933},
        abstract = {The rapid adoption of digital payment platforms such as Unified Payments Interface (UPI) has revolutionized financial transactions by offering speed, convenience, and accessibility. However, this growth has also led to a surge in fraudulent activities, where unsuspecting users fall victim to scams involving fake UPI IDs, QR codes, and malicious requests. To address this challenge, we propose an AI-enabled UPI Scam Detection and Reporting System that leverages machine learning and crowd-sourced intelligence to detect and prevent fraudulent transactions in real-time. The system analyses UPI ID patterns, transaction frequency, user engagement behaviour, and historical interactions to assign a dynamic scam likelihood score to unknown or suspicious UPI IDs. Based on this score, users receive instant alerts prior to initiating payments, thereby reducing the risk of financial loss. Furthermore, the framework integrates a reporting mechanism where users can flag suspicious UPI IDs and QR codes, which are then verified and incorporated into the fraud detection model to enhance accuracy over time. By combining behavioural analysis with community-driven reporting, the proposed solution strengthens the security of digital transactions and supports payment platforms such as Google Pay, PhonePe, and Paytm in combating fraud. This system aims to create a safer and more reliable digital payment ecosystem while empowering users with proactive scam prevention tools.},
        keywords = {},
        month = {August},
        }

Cite This Article

LAKSHMI, D. J. (2025). AI-Based UPI Scam Detection and Reporting System Using Crowdsourced Patterns & Verified Reports. International Journal of Innovative Research in Technology (IJIRT), 12(3), 3762–3765.

Related Articles