Deepfake Media Forensics: State of the Art and Challenges Ahead
Abstract
AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and Diffusion Models (DMs) are the main frameworks used to create Deepfakes, producing highly realistic yet fabricated content. While these technologies open up new creative possibilities, they also bring substantial ethical and security risks due to their potential misuse. The rise of such advanced media has led to the development of a cognitive bias known as Impostor Bias, where individuals doubt the authenticity of multimedia due to the awareness of AI's capabilities. As a result, Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques, especially Convolutional Neural Networks (CNNs). Research in forensic Deepfake technology encompasses five main areas: detection, attribution and recognition, passive authentication, detection in realistic scenarios, and active authentication. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.
Keywords
Cite
@article{arxiv.2408.00388,
title = {Deepfake Media Forensics: State of the Art and Challenges Ahead},
author = {Irene Amerini and Mauro Barni and Sebastiano Battiato and Paolo Bestagini and Giulia Boato and Tania Sari Bonaventura and Vittoria Bruni and Roberto Caldelli and Francesco De Natale and Rocco De Nicola and Luca Guarnera and Sara Mandelli and Gian Luca Marcialis and Marco Micheletto and Andrea Montibeller and Giulia Orru' and Alessandro Ortis and Pericle Perazzo and Giovanni Puglisi and Davide Salvi and Stefano Tubaro and Claudia Melis Tonti and Massimo Villari and Domenico Vitulano},
journal= {arXiv preprint arXiv:2408.00388},
year = {2024}
}