REVIEW 6 cited by
Detecting AI-Generated Video via Frame Consistency
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The escalating quality of video generated by advanced video generation methods results in new security challenges, while there have been few relevant research efforts: 1) There is no open-source dataset for generated video detection, 2) No generated video detection method has been proposed so far. To this end, we propose an open-source dataset and a detection method for generated video for the first time. First, we propose a scalable dataset consisting of 964 prompts, covering various forgery targets, scenes, behaviors, and actions, as well as various generation models with different architectures and generation methods, including the most popular commercial models like OpenAI's Sora and Google's Veo. Second, we found via probing experiments that spatial artifact-based detectors lack generalizability. Hence, we propose a simple yet effective \textbf{de}tection model based on \textbf{f}rame \textbf{co}nsistency (\textbf{DeCoF}), which focuses on temporal artifacts by eliminating the impact of spatial artifacts during feature learning. Extensive experiments demonstrate the efficacy of DeCoF in detecting videos generated by unseen video generation models and confirm its powerful generalizability across several commercially proprietary models.
Forward citations
Cited by 6 Pith papers
-
RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when wat...
-
VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
-
Detecting AI-Generated Video: A Vision-Language Dual-View Survey
AIGC-V detection should be treated as factual fidelity verification and organized by a four-layer vision-language dual-view taxonomy spanning cues, motion, cross-modal consistency, and world-level reasoning.
-
G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement
G2VD reaches over 90% accuracy and ~0.95 AUC on hard GenVidBench cross-domain tests by VAE counterfactual intervention plus dual-branch HSIC disentanglement, using only 10% of training data.
-
G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement
G2VD detects AI-generated videos from unseen generators by training on VAE-reconstructed real videos labeled fake, reaching ~92% overall accuracy on GenVidBench with only 10% of Pair1.
-
Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
NSG-VD detects AI-generated videos by measuring the ratio of spatial probability gradients to temporal density changes and comparing these 'NSG' features with a maximum mean discrepancy test.
Discussion (0). Sign in to comment.