Investigating the Impact of Pre-processing and Prediction Aggregation on the DeepFake Detection Task

Abstract

Recent advances in content generation technologies (widely known as DeepFakes) along with the online proliferation of manipulated media content render the detection of such manipulations a task of increasing importance. Even though there are many DeepFake detection methods, only a few focus on the impact of dataset preprocessing and the aggregation of frame-level to video-level prediction on model performance. In this paper, we propose a pre-processing step to improve the training data quality and examine its effect on the performance of DeepFake detection. We also propose and evaluate the effect of video-level prediction aggregation approaches. Experimental results show that the proposed pre-processing approach leads to considerable improvements in the performance of detection models, and the proposed prediction aggregation scheme further boosts the detection efficiency in cases where there are multiple faces in a video.

References in corpus (9)

• MesoNet: a Compact Facial Video Forgery Detection Network
• Media Forensics and DeepFakes: an overview
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
• BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
• ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
• The Deepfake Detection Challenge (DFDC) Preview Dataset

Cited by in corpus (3)

• Deepfake Video Detection Using Convolutional Vision Transformer
• Adversarially robust deepfake media detection using fused convolutional neural network predictions
• Video Transformer for Deepfake Detection with Incremental Learning