PhoneSathi: An AI-Powered Multilingual Mobile Web Application for Real-Time Scam Detection and Digital Safety in India

  • Unique Paper ID: 205651
  • Volume: 13
  • Issue: 1
  • PageNo: 8976-8982
  • Abstract:
  • The proliferation of smartphones in India has coincided with a sharp increase in mobile-based digital fraud, including SMS phishing (smishing), vishing, and malicious link propagation via messaging platforms. Existing security tools are primarily English-centric, non-explainable, and inaccessible to the large population of regional-language-first users. This paper presents PhoneSathi ("Phone Companion"), a multilingual Progressive Web Application (PWA) that provides real-time scam detection and digital safety guidance in English, Hindi, and Marathi. The system employs a keyword-heuristic analysis pipeline augmented by a Large Language Model (LLM) backend to analyse suspicious SMS messages, evaluate URL safety, classify phone numbers, and deliver conversational safety guidance with voice input and text-to-speech output. Built on a React/Vite frontend and the Base44 cloud platform, PhoneSathi is optimized for Android users in Maharashtra and broader India. We present the system architecture, threat model, multilingual design, honest evaluation of its capabilities and limitations, and discuss pathways toward more robust, AI-driven inclusive cybersecurity.

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{205651,
        author = {Manthan Raut and Arjun Raut and Atharv Rathi and Om Rane and Sujal Rathod and Vishwesh Deshmukh},
        title = {PhoneSathi: An AI-Powered Multilingual Mobile Web Application for Real-Time Scam Detection and Digital Safety in India},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {8976-8982},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205651},
        abstract = {The proliferation of smartphones in India has coincided with a sharp increase in mobile-based digital fraud, including SMS phishing (smishing), vishing, and malicious link propagation via messaging platforms. Existing security tools are primarily English-centric, non-explainable, and inaccessible to the large population of regional-language-first users. This paper presents PhoneSathi ("Phone Companion"), a multilingual Progressive Web Application (PWA) that provides real-time scam detection and digital safety guidance in English, Hindi, and Marathi. The system employs a keyword-heuristic analysis pipeline augmented by a Large Language Model (LLM) backend to analyse suspicious SMS messages, evaluate URL safety, classify phone numbers, and deliver conversational safety guidance with voice input and text-to-speech output. Built on a React/Vite frontend and the Base44 cloud platform, PhoneSathi is optimized for Android users in Maharashtra and broader India. We present the system architecture, threat model, multilingual design, honest evaluation of its capabilities and limitations, and discuss pathways toward more robust, AI-driven inclusive cybersecurity.},
        keywords = {Mobile security, scam detection, phishing, SMS analysis, multilingual AI, LLM, Progressive Web App, India, fraud prevention.},
        month = {June},
        }

Cite This Article

Raut, M., & Raut, A., & Rathi, A., & Rane, O., & Rathod, S., & Deshmukh, V. (2026). PhoneSathi: An AI-Powered Multilingual Mobile Web Application for Real-Time Scam Detection and Digital Safety in India. International Journal of Innovative Research in Technology (IJIRT), 13(1), 8976–8982.

Related Articles