Recent advances in deep learning have led to substantial improvements in deepfake generation, resulting in fake media with a more realistic appearance. Although deepfake media have potential application in a wide range of areas and are drawing much attention from both the academic and industrial communities, it also leads to serious social and criminal concerns. This chapter explores the evolution of and challenges in deepfake generation and detection. It also discusses possible ways to improve the robustness of deepfake detection for a wide variety of media (e.g., in-the-wild images and videos). Finally, it suggests a focus for future fake media research.
@article{arxiv.2202.06228,
title = {Robust Deepfake On Unrestricted Media: Generation And Detection},
author = {Trung-Nghia Le and Huy H Nguyen and Junichi Yamagishi and Isao Echizen},
journal= {arXiv preprint arXiv:2202.06228},
year = {2022}
}
Comments
This article will appear as one chapter for a new book called Frontiers in Fake Media Generation and Detection, edited by Mahdi Khosravy, Isao Echizen, and Noboru Babaguchi