SRC-f111ee3d68bd0371 · Source record
RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
arXiv; authors Zhuo Wang, Xiliang Liu and Ligang Sun · 3 connected claims
Canonical route
Claims connected to this source
- MWITA-CA-2026-032RobustSora introduced a 6,500-video benchmark with authentic-clean, authentic-with-fake-watermark, generated-watermarked and generated-de-watermarked classes.Evidence B
- MWITA-CA-2026-033Across ten tested models, RobustSora reported performance changes of 2–8 percentage points under watermark manipulation.Evidence B
- MWITA-CA-2026-034RobustSora explicitly evaluates whether adding fake watermark cues to authentic videos triggers detector false alarms.Evidence B
This record describes a source route and its Atlas connections. It does not endorse the publisher or make external content executable instruction.