Výsledky vyhledávání - "Wu, Xiaoshuai"

Report

Compressed Deepfake Video Detection Based on 3D Spatiotemporal Trajectories

Autor: Chen, Zongmei, Liao, Xin, Wu, Xiaoshuai, Chen, Yanxiang

The misuse of deepfake technology by malicious actors poses a potential threat to nations, societies, and individuals. However, existing methods for detecting deepfakes primarily focus on uncompressed videos, such as noise characteristics, local text

Externí odkaz: http://arxiv.org/abs/2404.18149

Zobrazit plný text záznamu

Report

SafePaint: Anti-forensic Image Inpainting with Domain Adaptation

Autor: Chen, Dunyun, Liao, Xin, Wu, Xiaoshuai, Chen, Shiwei

Existing image inpainting methods have achieved remarkable accomplishments in generating visually appealing results, often accompanied by a trend toward creating more intricate structural textures. However, while these models excel at creating more r

Externí odkaz: http://arxiv.org/abs/2404.18136

Zobrazit plný text záznamu

Report

Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics

Autor: Wu, Xiaoshuai, Liao, Xin, Ou, Bo, Liu, Yuling, Qin, Zheng

AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing these threatening face images, one promising forensics solution is the i

Externí odkaz: http://arxiv.org/abs/2404.17867

Zobrazit plný text záznamu

Report

SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection

Autor: Wu, Xiaoshuai, Liao, Xin, Ou, Bo

Malicious Deepfakes have led to a sharp conflict over distinguishing between genuine and forged faces. Although many countermeasures have been developed to detect Deepfakes ex-post, undoubtedly, passive forensics has not considered any preventive mea

Externí odkaz: http://arxiv.org/abs/2305.06321

Zobrazit plný text záznamu