MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122102 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'comparative phishing detection system using bert and large language models.'
Inventor(s) include Dr. Mohankumar B; and Justin Wilson John.
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 comparative phishing detection system including a data preprocessing module configured to receive email data and convert the email data into tokenized representations suitable for analysis by machine learning models, a transformer-based classification module including a transformer model configured to process the tokenized representations and generate binary classification outputs indicating whether emails are phishing or legitimate, a large language model-based classification module including a large language model configured to receive structured prompts containing email content and generate classification responses through inference, a performance evaluation module configured to compute classification metrics including accuracy, precision, recall, F1-score, and ROC-AUC values for both the transformer-based classification module and the large language model-based classification module, and a comparative analysis module configured to generate performance comparisons between the transformer-based classification module and the large language model-based classification module based on the computed classification metrics."
Disclaimer: Curated by HT Syndication.
