Living in the Age of Deepfakes: A Bibliometric Exploration of Trends, Challenges, and Detection Approaches

Abstract

In an era where all information can be reached with one click and by using the internet, the risk has increased in a significant manner. Deepfakes are one of the main threats on the internet, and affect society by influencing and altering information, decisions, and actions. The rise of artificial intelligence (AI) has simplified the creation of deepfakes, allowing even novice users to generate false information in order to create propaganda. One of the most prevalent methods of falsification involves images, as they constitute the most impactful element with which a reader engages. The second most common method pertains to videos, which viewers often interact with. Two major events led to an increase in the number of deepfake images on the internet, namely the COVID-19 pandemic and the Russia–Ukraine conflict. Together with the ongoing “revolution” in AI, deepfake information has expanded at the fastest rate, impacting each of us. In order to reduce the risk of misinformation, users must be aware of the deepfake phenomenon they are exposed to. This also means encouraging users to more thoroughly consider the sources from which they obtain information, leading to a culture of caution regarding any new information they receive. The purpose of the analysis is to extract the most relevant articles related to the deepfake domain. Using specific keywords, a database was extracted from Clarivate Analytics’ Web of Science Core Collection. Given the significant annual growth rate of 161.38% and the relatively brief period between 2018 and 2023, the research community demonstrated keen interest in the issue of deepfakes, positioning it as one of the most forward-looking subjects in technology. This analysis aims to identify key authors, examine collaborative efforts among them, explore the primary topics under scrutiny, and highlight major keywords, bigrams, or trigrams utilized. Additionally, this document outlines potential strategies to combat the proliferation of deepfakes in order to preserve information trust.