MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123034 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'machine learning system for phishing url detection.'
Inventor(s) include Dr. Mohankumar B; Sameer Raj; Bharat Kumar Garg; and Kushagra Sharma.
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 a computer-implemented method for detecting phishing URLs. The method includes receiving a URL as input, extracting features from the URL and associated webpage content including URL-based, content-based, and security-based features, preprocessing the extracted features including normalizing, applying an ensemble of trained machine learning models to the preprocessed features, and generating a binary classification output indicating whether the URL is phishing or legitimate. The feature extraction module extracts twenty-one distinct features including URL length, domain length, letter-to-digit ratio, number of images, JavaScript elements, and security indicators. The ensemble machine learning module combines XGBoost, CatBoost, and LightGBM algorithms using weighted voting techniques. The prediction engine processes normalized features through the trained models to generate binary classifications with confidence scores for real-time phishing detection."
Disclaimer: Curated by HT Syndication.
