MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541114858 A) filed by Sri Sairam Engineering College, Chennai, Tamil Nadu, on Nov. 21, 2025, for 'ai driven multilingual phishing detection framework for transliterated text using hybrid machine and deep learning models.'
Inventor(s) include Gengaraj P; Shanth S; Karthik S; Manikandan M; Abhiram R; and K Iswarya.
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: "This invention consists of a framework for detecting phishing that is multilingual, and powered by AL which can classify text messages as either phishing or legitimate. The framework is designed to detect transliterated (Latin-Tamil) and multilingual text formats, and ultimately overcomes the limitations of Englishcentric phishing detection technology that is typically used. When the framework detects text, it passes through a preprocessing step as well as several features extracted by NLP, which converts the raw text to a more structured representation, using TF-IDF and n-gram techniques. For classification, the framework employs a hybrid architecture with machine learning models (Support Vector Machine, Random Forest) and deep learning models (Recurrent Neural Network. Long Short-Term Memory). To improve the stability of cross-lingual learning, the framework supports more than one loss function, specifically: binary cross-entropy, sparse categorical cross-entropy, and hinge-loss. For the framework has been evaluated, and validated both in the detection of phishing efficacy, and adaptation to different linguistic contexts. Thus, the invention provides a scalable and language-aware real-time solution for detecting phishing, increasing cybersecurity resilience due to evolving phishing threats in multilingual communication channels."
Disclaimer: Curated by HT Syndication.
