Rethinking the up-sampling operations in cnn-based generative network for generalizable deepfake detection

C Tan, Y Zhao, S Wei, G Gu, P Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recently the proliferation of highly realistic synthetic images facilitated through a variety of
GANs and Diffusions has significantly heightened the susceptibility to misuse. While the …

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

A Liu, S Xue, J Gan, J Wan, Y Liang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Domain generalization (DG) based Face Anti-Spoofing (FAS) aims to improve the
model's performance on unseen domains. Existing methods either rely on domain labels to …

Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis

HH Nguyen, J Yamagishi, I Echizen - arXiv preprint arXiv:2405.00355, 2024 - arxiv.org
This paper investigates the effectiveness of self-supervised pre-trained transformers
compared to supervised pre-trained transformers and conventional neural networks …

Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet

D Tariang, R Corvi, D Cozzolino, G Poggi… - arXiv preprint arXiv …, 2024 - arxiv.org
Synthetic Image Verification in the Era of Generative AI: What Works and What Isn’t There Yet
Page 1 1 Synthetic Image Verification in the Era of Generative AI: What Works and What Isn’t …

A Survey of Defenses against AI-generated Visual Media: Detection, Disruption, and Authentication

J Deng, C Lin, Z Zhao, S Liu, Q Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Deep generative models have demonstrated impressive performance in various computer
vision applications, including image synthesis, video generation, and medical analysis …