From deepfake to deep useful: risks and opportunities through a systematic literature review
Nikolaos Misirlis, Harris Bin Munawar

TL;DR
This systematic literature review explores the dual nature of deepfake technology, highlighting societal threats like misinformation and potential benefits in entertainment and education, while emphasizing the need for detection and ethical considerations.
Contribution
First systematic review in the field analyzing both risks and opportunities of deepfake technology with a focus on detection and ethical issues.
Findings
High scientific interest in deepfake detection algorithms
Deepfake technology poses threats to society and democracy
Potential benefits in entertainment, gaming, education, and public life
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection · Image and Video Quality Assessment · Generative Adversarial Networks and Image Synthesis
