SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection
SafeGuard:用于社会风险AI生成视频检测的多智能体感知-推理框架
机构 * University of Science and Technology of China(中国科学技术大学) ; King Abdullah University of Science and Technology(阿卜杜拉国王科技大学) ; Vast Intelligence Lab(旷视智能实验室)
AI总结 针对AI生成视频检测挑战,提出SafeGuard多智能体框架,通过感知求解器与验证器协作,引入SafeVid基准,实验证明其泛化性佳,提升检测准确率。
Comments Accepted to ECCV 2026, The code and dataset are publicly available at https://github.com/williamw99/SafeGuard