MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123210 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 6, 2025, for 'ai-powered multi-modal scam detection system.'
Inventor(s) include Dr. Sudha S; Gracy Agarwal; and Pranjal Pandey.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides an AI-powered multi-modal scam detection system including a data input interface configured to receive user-submitted content including URLs, QR code images, voice call recordings, and SMS text messages, detection modules where each module analyzes different input content for scam detection, AI-based classification models within the detection modules configured to automatically classify input content as legitimate or fraudulent, an integration mechanism that unifies the detection modules into a single system, and real-time processing capability configured to provide classification results without delay. The system processes multiple fraud vectors simultaneously through specialized machine learning algorithms including XGBoost classifiers for phishing URL detection, Convolutional Neural Networks for QR code visual analysis, Transformer-based models for voice call classification, and Logistic Regression with TF-IDF vectorization for SMS scam detection, enabling comprehensive protection against evolving digital fraud schemes."
Disclaimer: Curated by HT Syndication.
