A statistical analysis for deepfake videos forgery traces recognition followed by a fine-tuned InceptionResNetV2 detection technique.

Abstract

Deepfake videos are growing progressively more competent because of the rapid advancements in artificial intelligence and deep learning technology. This has led to substantial problems around propaganda, privacy, and security. This research provides an analytically novel method for detecting deepfake videos using temporal discrepancies of the various statistical features of video at the pixel level, followed by a deep learning algorithm. To detect minute aberrations typical of deepfake manipulations, this study focuses on both spatial information inside individual frames and temporal correlations between subsequent frames. This study primarily provides a novel Euclidean distance variation probability score value for directly commenting on the authenticity of a deepfake video. Next, fine-tuning of InceptionResNetV2 with the addition of a dense layer is trained FaceForensics++ for deepfake detection. The proposed fine-tuned model outperforms the existing techniques as its testing accuracy on unseen data outperforms the existing methods. The propsd method achieved an accuracy of 99.80% for FF++ dataset and 97.60% accuracy for CelebDF dataset.