Unmasking the Illusion: The Tech Behind Deepfakes

Authors

Michele Brienza
Sapienza University of Rome
https://orcid.org/0009-0000-1549-9500
Domenico Daniele Bloisi
International University of Rome - UNINT
https://orcid.org/0000-0003-0339-8651
Daniele Nardi
Faculty of Information Engineering, Computer Science, and Statistics, Sapienza University of Rome
https://orcid.org/0000-0001-6606-200X
DOI: https://doi.org/10.18690/um.feri.2.2026.1

Synopsis

The chapter provides an overview of the technology behind deepfakes, describing what a deepfake is and how it is created. The chapter is structured around three sections: (i) theoretical foundations of artificial intelligence, machine learning, and deep learning, (ii) generative models and synthetic data, and (iii) the synthetic media toolkit. Firstly, it describes AI evolution, starting from the early stages leading up to the latest models that can generate data. The latest models are then described, highlighting their capabilities and explaining how these models open a wide range of opportunities, as well as the concerns regarding the generation of highly realistic data that can deceive users, as is the case with deepfakes. Finally, knowledge of how the machines learn from the data helps in using these tools. A clear understanding of the process behind the technology leads to unmasking the illusion and understanding how the technology works, enabling informed use.

Author Biographies

Michele Brienza, Sapienza University of Rome

Michele Brienza is currently a PhD student in Artificial Intelligence at Sapienza University of Rome. With a master’s degree in Computer Science Engineering his research focuses on embodied AI; in particular, in the use of generative AI within physical systems such as robots operating in real environments that need to cooperate with humans. He works with CINI on the EU Horizon project SOLARIS, providing technical support for the generation of deepfakes to evaluate the impact on democracies.

Rome, Italiy. E-mail: brienza@diag.uniroma1.it

Domenico Daniele Bloisi, International University of Rome - UNINT

Domenico Daniele Bloisi is an associate professor of Artificial Intelligence at the UNINT International University of Rome (Italy). Previously, he was associate professor at the University of Basilicata (Italy), assistant professor at the University of Verona (Italy), and assistant professor at Sapienza University of Rome (Italy). He has been visiting professor at the University of Pennsylvania (USA. He is the author of more than 80 peer-reviewed papers, with a focus on medical image analysis, multi-robot coordination, visual perception and information fusion. Dr. Bloisi is WP leader of two EU funded projects and team manager of the SPQR robot soccer team.

Rome, Italy. E-mail: domenico.bloisi@unint.eu

Daniele Nardi, Faculty of Information Engineering, Computer Science, and Statistics, Sapienza University of Rome

Daniele Nardi is a Full Professor of Artificial Intelligence at the Faculty of Information Engineering, Computer Science, and Statistics of Sapienza University of Rome. He is a member of the Department of Engineering for Information, Automation and Management (DIAG). He is responsible for the "Cooperative Cognitive Robots" Laboratory and several European projects in FP7 and H2020. Daniele Nardi is the author of numerous publications in the field of Artificial Intelligence and Robotics, having previously served as President of the RoboCup Federation and Director of the AI and Intelligent Systems Laboratory of the National Interuniversity Consortium for Informatics (CINI).

Rome, Italy. E-mail: nardi@diag.uniroma1.it

Downloads

PDF

Volume

Deepfakes, Democracy, and the Ethics of Synthetic Media: A Synthesis of the SOLARIS Project

Pages

9-24

Published

February 10, 2026

Categories

Copyright (c) 2026 University of Maribor, University of Maribor Press

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Brienza, M., Domenico Daniele, D. D., & Nardi, D. (2026). Unmasking the Illusion: The Tech Behind Deepfakes. In Y. Yousefi, L. Conover, I. Mlakar, & F. Russo (Eds.), Deepfakes, Democracy, and the Ethics of Synthetic Media: A Synthesis of the SOLARIS Project (pp. 9-24). University of Maribor Press. https://doi.org/10.18690/um.feri.2.2026.1