3 papers
cs.CV2026
HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales
Wenbo Xu, Zhimin Chen, Xiaojie Liang +3
Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, presenting unprecedented challenges to…
cs.CV2026
Bridging the Micro--Macro Gap: Frequency-Aware Semantic Alignment for Image Manipulation Localization
Xiaojie Liang, Zhimin Chen, Ziqi Sheng +1
As generative image editing advances, image manipulation localization (IML) must handle both traditional manipulations with conspicuous forensic artifacts and diffusion-generated e…
cs.CR2026
Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service
Zhimin Chen, Xiaojie Liang, Wenbo Xu +2
Embedding-as-a-Service (EaaS) has become an important semantic infrastructure for natural language and multimedia applications, but it is highly vulnerable to model stealing and co…