Paper summary
Paper summary: Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
RA-Bench pairs 1,830 real crisis videos with 16,056 generated clips from nine generators, and finds that no family of AI-video detectors generalises consistently, including when videos are re-shared on social media.
- Real videos act as anchors, so detectors are tested on generated clips of the same kinds of crisis events.
- None of the three detector families (traditional, zero-shot multimodal, fine-tuned MLLMs) generalised consistently.