MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641043527 A) filed by Nandha College Of Technology, Vaikkaalmedu, Tamil Nadu, on April 6, for 'smart phishing detection leveraged using biderctional encoder representations from transformer model.'
Inventor(s) include B M S Javed Ahamed; H Aani Preethika; D Dhanishikaa; N Ishanth; and P G Philip Bmoj.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The present invention describes a Smart Phishing Detection System using BERT and XG Boost to detect phishing emails automatically. The system analyzes incoming emails using preprocessing, metadata analysis, rule-based detection, and natural language processing techniques. The BERT model extracts contextual features from email content, while the XG Boost classifier determines whether the email is legitimate, suspicious, or phishing. A risk scoring module evaluates the severity of the threat and generates automated responses such as allowing safe emails, reporting suspicious emails, or moving phishing emails to spam. The proposed system significantly improves email security by combining deep learning and machine learning approaches for accurate phishing detection."
Disclaimer: Curated by HT Syndication.
