MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122137 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid cnn-snn system for deepfake video detection.'
Inventor(s) include Dr Padmavathy T; Blessy Kavuturu; Arpita Umesh Patil; and Meet Movaliya.
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 hybrid deepfake detection system comprising a video preprocessing module configured to extract frames from input video data and detect facial regions within the extracted frames, a convolutional neural network module configured to extract spatial features from the detected facial regions, a spiking neural network module configured to analyze temporal patterns across frame sequences, a feature fusion module configured to combine the spatial features and temporal features into a unified representation, and a classification module configured to generate a binary classification output indicating whether the input video data contains authentic or deepfake content. The convolutional neural network module processes individual frames to identify visual inconsistencies, texture anomalies, and lighting irregularities that indicate synthetic manipulation. The spiking neural network module converts extracted frames into spike trains and implements Leaky Integrate-and-Fire neuron models for event-driven temporal processing."
Disclaimer: Curated by HT Syndication.
