Enhancing UPI Transaction Security Through Colour Pattern Authentication

DOI

10.2991/978-94-6239-616-6_23How to use a DOI?

Keywords

UPI Security; Colour Pattern Authentication; Covert Attentional Shoulder Surfing (CASS); Behavioural Biometrics; Recurrent Neural Network (RNN); Fraud Detection; Anomaly Detection; Graphical Passwords; Mobile Payment Security; Machine Learning; User Authentication; Transaction Privacy

Abstract

The exponential growth of Unified Payments Interface (UPI) transactions has raised significant concerns over user authentication security, especially in protecting against shoulder-surfing and fraudulent access. This paper proposes a dual-layer security framework that integrates Covert Attentional Shoulder-Surfing (CASS) — a colour-pattern-based graphical authentication system — with Recurrent Neural Network (RNN)-based Behavioural biometrics for real-time anomaly detection. The CASS scheme replaces static numeric PINs with dynamic colour grids, reducing the risk of observation attacks, while the RNN model analyzes user interaction Behaviour to detect suspicious or abnormal activities. Experimental evaluation was conducted using a synthetic UPI transaction dataset of 10,000 records generated through simulated user sessions. Results demonstrated an authentication accuracy of 96.4%, with the RNN achieving 93.8% fraud detection accuracy and minimal latency (<1.5 s) per transaction. Usability testing with 40 participants showed that 87% found colour-pattern authentication more intuitive than traditional PIN entry. The proposed hybrid framework enhances both usability and security while maintaining lightweight computation suitable for mobile deployment.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - G. Prabu
AU  - G. Nelson
AU  - M. Gowtham
AU  - S. Yogesh
PY  - 2026
DA  - 2026/03/31
TI  - Enhancing UPI Transaction Security Through Colour Pattern Authentication
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 276
EP  - 285
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_23
DO  - 10.2991/978-94-6239-616-6_23
ID  - Prabu2026
ER  -