Swapped Face Detection: AI-Based Method and Evaluation for Different Face Swap Algorithms

Deepfake images have become a major problem in today’s digital landscape. Such images are usually created using advanced machine learning techniques. These fake images can deceive viewers, posing risks to privacy, security, and trust. In this paper we introduce an innovative approach to detect deepfake by analyzing facial landmarks and computing corresponding expert features, train multiple classifier models based on three sets of features and achieve an accuracy of 0.682 and F1-score of 0.680. Using the coefficients of the resulting models, we evaluate the importance of features and identify the most important ones.