Diya Garg

A Hybrid Feature Fusion Approach for Cross-Quality Deepfake Detection – F2CV

A compression-aware multimodal deepfake detection framework that jointly exploits spatial, frequency and motion information from compressed videos and achieves an accuracy level of 99.63% and Area Under Curve of 99.83% on the FaceForensics++ (FF++) dataset, improving robustness to compression artifacts and enhances dee...