3 papers
cs.CV2026
SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection
Wenlin Wu, Sheng Zhou, Peipei Song +3
As video generation paradigms evolve from localized manipulation to full-scene synthesis, AI-generated video detection becomes increasingly challenging, as forgeries exhibit cohere…
cs.CV2026
Spectral Tail Auxiliary Learning for AI-Generated Image Detection
Xingyi Li, Jiahui Zhang, Yiheng Li +2
As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. M…
cs.CV2026
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
Yiheng Li, Yang Yang, Zichang Tan +3
As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to…