MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049894 A) filed by Easwari Engineering College; and Srm Institute Of Science And Technology, Ramapuram Campus, Chennai, Tamil Nadu, on April 20, for 'a web-based integrated system for fake news and deepfake detection using machine learning and deep learning.'
Inventor(s) include Mohammed Mohseen A; Sri Rajarajeswaran B; and Dr. G. Jeyaram.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The present invention introduces a unified web-based system designed to detect misinformation in the form of fake news and deepfake media using advanced machine learning and deep learning techniques. The system integrates both text and multimedia analysis within a single platform. The text analysis module applies preprocessing methods such as tokenization, stop-word removal, and TF-IDF vectorization, followed by classification using a Passive Aggressive algorithm to identify whether the content is real or fake. The multimedia module analyzes images and videos by extracting frames, performing normalization, and utilizing a ResNet-based deep learning model to detect manipulated media. The system delivers real-time results through an intuitive and user-friendly interface, allowing users to quickly verify content authenticity. By combining textual and visual analysis, the proposed system ensures improved accuracy, scalability, and efficiency, making it a practical and reliable solution for addressing the growing challenge of misinformation in digital platforms."
Disclaimer: Curated by HT Syndication.
