Comparative Analysis and Evaluation of CNN Models for Deepfake Detection
Pattrick Ritter, Devan Lucian, Anderies, Andry Chowanda
Abstract
Deepfake technology has become a significant concern due to its ability to create highly realistic fake videos and images, leading to the potential deception of individuals. Detecting deepfakes has become a critical research area in computer vision and multimedia forensics. This paper presents a comparative analysis of deepfake detection models, focusing on evaluating their accuracy and robustness. Four CNN models, namely ResNet-152, MobilenetV3, Convnext Large, and EffecientNetB7, were implemented and trained using a custom dataset obtained from FaceForensics++. The models were evaluated based on training accuracy, average loss, and testing accuracy. An LSTM layer was also incorporated into each model's architecture to leverage sequential information. The results demonstrate varying performance among the models, with EfficientNet B7 achieving the highest testing accuracy of 75%. The findings of this study provide insights for future research in this critical area.