MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541134060 A) filed by Nitte Meenakshi Institute Of Technology, Nitte; Dr. Ranjan Kumar H S; Ms. Sharmila Shanthi Sequeira; and Ms. Shabana S, Bangalore, Karnataka, on Dec. 31, 2025, for 'malicious url detection system using machine learning.'
Inventor(s) include Nitte Meenakshi Institute Technology, Nitte; Dr. Ranjan Kumar H S; Ms. Sharmila Shanthi Sequeira; and Ms. Shabana S.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to a cybersecurity system for detecting malicious URLs using machine learning techniques. The system addresses the critical threat posed by phishing attacks, malware distribution, spam campaigns, and botnet communications conducted through deceptive URLs. Traditional blacklist-based approaches fail to detect zero-day threats and newly created malicious URLs, creating significant security gaps. The system comprises five integrated modules: (1) Data Collection acquiring balanced datasets from trusted sources, (2) Data Preprocessing performing duplicate removal, normalization, filtering, and SMOTE-based class balancing, (3) Feature Extraction computing 45 features across lexical (23), host-based (8), and rule-based (10) categories, (4) Model Training implementing Random Forest and XGBoost classifiers achieving 100% test accuracy, and (5) Deployment Interface providing URL Checker and Gmail Scanner applications through web-based Gradio interfaces. The present invention ensures lightweight real-time detection suitable for browser integration, explainable predictions through feature importance analysis, zero-day threat detection through behavioral pattern learning, and practical deployment enabling immediate protection for end-users against evolving cyber threats without requiring website content fetching or blacklist dependencies."
Disclaimer: Curated by HT Syndication.
