From deepfake to deep useful: risks and opportunities through a systematic literature review (2311.15809v1)

Abstract: Deepfake videos are defined as a resulting media from the synthesis of different persons images and videos, mostly faces, replacing a real one. The easy spread of such videos leads to elevated misinformation and represents a threat to society and democracy today. The present study aims to collect and analyze the relevant literature through a systematic procedure. We present 27 articles from scientific databases revealing threats to society, democracies, the political life but present as well advantages of this technology in entertainment, gaming, education, and public life. The research indicates high scientific interest in deepfake detection algorithms as well as the ethical aspect of such technology. This article covers the scientific gap since, to the best of our knowledge, this is the first systematic literature review in the field. A discussion has already started among academics and practitioners concerning the spread of fake news. The next step of fake news considers the use of artificial intelligence and machine learning algorithms that create hyper-realistic videos, called deepfake. Deepfake technology has continuously attracted the attention of scholars over the last 3 years more and more. The importance of conducting research in this field derives from the necessity to understand the theory. The first contextual approach is related to the epistemological points of view of the concept. The second one is related to the phenomenological disadvantages of the field. Despite that, the authors will try to focus not only on the disadvantages of the field but also on the positive aspects of the technology.