RA-Bench：AI生成视频检测基准揭示现有检测器在危机事件中的不足
原标题：Paper page - Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
AI 摘要
Hugging Face 每日论文页面发布了一篇关于AI生成视频检测的论文，提出了新基准RA-Bench，包含17,886个视频，评估了多个检测器和生成器。研究发现当前检测器在真实危机事件视频上泛化能力差，且社交媒体传播会降低检测可靠性。该研究强调了开发更鲁棒检测器的必要性。
正文节选
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Abstract A new benchmark for AI-generated video detection reveals that current detectors fail to generalize across realistic crisis-related videos and become less reliable as content spreads socially. Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantia