About this document
Final Project PDF by umeshgoudediga is a document available to read on EtoBox.
The report presents a multi-modal deepfake detection framework that analyzes both audio and video streams to identify inconsistencies in manipulated media. Utilizing Vision Transformers for spatial analysis and Bi-GRU for audio processing, the system achieves strong performance metrics, including an accuracy of 75.16% and an AUC of 0.8173. The integration of Explainable AI techniques enhances the model
- Author
- umeshgoudediga
- Language
- EN