Secure UPI: Machine Learning Based Android Application for Real-Time Fraud Detection Using CNN

Read full text Summarise with VIRAT
Cited by: 0
References: 5

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The rapid growth of Unified Payments Interface (UPI) transactions in India has significantly increased the risk of digital payment fraud.Traditional rule-based fraud detection systems are unable to detect evolving fraud patterns effectively.This paper proposes a Secure UPI Fraud Detection System using a Convolutional Neural Network (CNN) integrated into an Android application for real-time fraud prediction.The system analyzes transaction features such as transaction amount, frequency, and behavioral attributes to classify transactions as legitimate or fraudulent.The trained model is deployed on a Python-based backend server and communicates with the Android application through secure RESTful APIs.Multi-layer security mechanisms including OTPbased authentication and encrypted communication enhance system reliability.Experimental results demonstrate approximately 95% classification accuracy with improved fraud detection performance, hereby improving transaction safety and reducing financial risk.The proposed system provides an intelligent, scalable, and secure framework for real-time digital payment fraud prevention.

Fields of Study & Subjects

Imbalanced Data Classification Techniques Privacy-Preserving Technologies in Data User Authentication and Security Systems

Publication details

Journal / source
International Research Journal of Modernization in Engineering Technology and Science
Publication date
25 March 2026
Language
EN