CyberText Shield: AI-Powered Protection for Secure and Scam-Free Messages

Assistant Professor Dept. of CSE-DS Acharya Institute of Technology Bengaluru, Karnataka, India
Dept. of CSE-DS Acharya Institute of Technology Bengaluru, Karnataka, India
Dept. of CSE-DS Acharya Institute of Technology Bengaluru, Karnataka, India
Dept. of CSE-DS Acharya Institute of Technology Bengaluru, Karnataka, India
Dept. of CSE-DS Acharya Institute of Technology Bengaluru, Karnataka, India

This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

The rapid proliferation of mobile communication has established smishing as a primary vector for cyber-social attacks, leveraging user trust to facilitate unauthorized data exfiltration and malware delivery. Conventional defensive mechanisms, including static keyword filters and sender blacklists, increasingly struggle with high false-positive rates and fail to neutralize sophisticated adversarial permutations. To address these limitations, we propose CyberText Shield, a specialized mobile-centric framework for real-time smishing detection. At its technical core, the system transitions from traditional sequential text analysis to high-order relational modeling via Hypergraph Neural Networks (HGNN). By representing message tokens, sender metadata, and contextual features as nodes connected through an incidence-based hypergraph structure, the model captures non-linear dependencies that standard deep learning architectures frequently overlook. We implement an edge-optimized HGNN inference engine tailored for resource-constrained hardware, achieving a detection accuracy of 91% with a critical processing latency of less than 100ms per message.This integration of lightweight graph-based learning with a user-centric educational interface provides a robust, interpretable, and scalable defense against the evolving landscape of mobile phishing threats. Experimental results validate the system's effectiveness in balancing computational efficiency with superior predictive performance in real-world deployment scenarios.