[2604.04634] Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale

Computer Science > Computer Vision and Pattern Recognition arXiv:2604.04634 (cs) [Submitted on 6 Apr 2026] Title:Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale Authors:Zhengcen Li, Chenyang Jiang, Hang Zhao, Shiyang Zhou, Yunyang Mo, Feng Gao, Fan Yang, Qiben Shan, Shaocong Wu, Jingyong Su View a PDF of the paper titled Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale, by Zhengcen Li and 9 other authors View PDF HTML (experimental) Abstract:The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media, raising significant societal concerns regarding the spread of misinformation. However, current detection methods suffer from critical limitations. They rely on preprocessing operations like fixed-resolution resizing and cropping. These operations not only discard subtle, high-frequency forgery traces but also cause spatial distortion and significant information loss. Furthermore, existing methods are often trained and evaluated on outdated datasets that fail to capture the sophistication of modern generative models. To address these challenges, we introduce a comprehensive dataset and a novel detection framework. First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators, along with Magic Videos benchmark designed specifically for evaluating ultra-realistic synthetic content. In addition, we propose a novel detec...