The Threat of Deepfakes to Computer and Human Visions

Pavel Korshunov, Sébastien Marcel

Abstract: Deepfake videos, where DeepFakea person’s face is automatically swapped with a face of someone else, are becoming easier to generate with more realistic results. The concern for the impact of the widespread deepfakeDeepFake videos on the societal trust in video recordings is growing. In this chapter, we demonstrate how dangerous deepfakesDeepFake are for both human and computer visions by showing how well these videos can fool face recognitionFace recognition algorithms and naïve human subjects. We also show how well the state-of-the-art deepfake detectionDeepFake detection algorithms can detect deepfakesDeepFake and whether they can outperform humans.