Regulating Deep Fakes: Legal and Ethical Considerations

Abstract

Deep fakes have become a buzzword discussed widely among legal and technology experts. The term ‘deep fakes’ refers to face-swapping technologies that enable a quick creation of fake images or videos which appear incredibly realistic. This paper explains the technologies behind the creation of deep fakes and offers four categories of deep fakes (deep fake porn, deep fakes in political campaigns, deep fakes for commercial uses and creative deep fakes). The authors of this paper address ethical and regulatory aspects each of those four categories of deep fakes. Since the first deep fakes were used for malicious and socially detrimental purposes (e.g., revenge porn and political campaigns), the authors highlight that these deep fakes - like many other technologies in the past - initially are confronted with fear. Since deep fakes are likely to be more widely adopted in the future, the authors highlight various social and legal challenges which the regulators and the society will have to face. The paper also touches upon the potential role of online content dissemination platforms and governments in addressing deep fakes. The authors of this paper also offer three suggestions - one from a technology point of view and two from a regulatory angle - on how to curtail the advancement of deep fakes.

Keywords: Deep fakes, privacy, face-swapping, artificial intelligence, machine learning, law, copyright, regulation, free speech