MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202521058617 A) filed by Aryan Nikam; and Jyotsna Nikam, Raigad, Maharashtra, on June 18, for 'a system and method for real-time detection and alerting of synthetic video and audio content, including live video calls, on a mobile computing device.'
Inventor(s) include Aryan Nikam.
The application for the patent was published on July 11, under issue no. 28/2025.
According to the abstract released by the Intellectual Property India: "The present invention discloses a system and method for real-time detection and classification of synthetic video content, commonly referred to as deepfake videos, displayed on a mobile device. The system includes a hardware-integrated screen recording module, a frame extractor, a deep learning-based classification engine, a result aggregator, and a notification module. Upon user initiation, a floating interface triggers short-duration screen recording, which is segmented into frames and analyzed using a pre-trained neural network. A voting mechanism determines whether the video is real or synthetic. The system operates in the background, deletes recorded media irreversibly for privacy, and notifies the user via native push alerts. It also supports manual upload of stored video files for analysis. Additionally, when microphone access is enabled, the system performs audio authenticity classification using machine learning models trained to detect synthetic speech. This dual-mode detection capability enhances reliability in identifying manipulated content across both visual and voice-based media streams."
Disclaimer: Curated by HT Syndication.
