SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection
2026-07-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of detecting AI-generated videos that look very realistic and follow normal physical and social rules. They point out that current tests mostly check for obvious visual glitches but miss videos that break real-world logic or social behavior. To solve this, they created SafeGuard, a system combining detailed forensic checks with reasoning about what makes sense physically and socially in videos. They also made a new video dataset called SafeVid to better test these abilities. Their experiments show SafeGuard works better than previous methods at spotting fakes across multiple tests.
AI-generated videovideo forgery detectionperceptual artifactssemantic reasoningphysical plausibilitystructural coherencesocial logicforensic evidencebenchmark datasethierarchical solver
Authors
Wenlin Wu, Sheng Zhou, Peipei Song, Wenhao Wang, Junbin Xiao, Xun Yang
Abstract
As video generation paradigms evolve from localized manipulation to full-scene synthesis, AI-generated video detection becomes increasingly challenging, as forgeries exhibit coherent global structure and high perceptual realism. However, existing benchmarks are biased toward perceptual fidelity and primarily evaluate detectors based on perceptual artifacts, providing limited coverage of scenarios that require reasoning about violations of physical laws, structural coherence, or social logic. This dataset bias shapes current approaches and results in a Perception-Reasoning Gap: artifact-centric models capture low-level statistical irregularities yet lack semantic inference, whereas vision-language models perform semantic reasoning but remain insensitive to fine-grained forensic cues. To bridge this gap, we propose SafeGuard, a multi-agent framework that enables collaborative specialization between forensic perception and semantic reasoning. A hierarchical perceptual solver extracts fine-grained forensic evidence, while a self-reflective verifier enforces consistency between semantic inference and physical plausibility, forming an interpretable evidence chain. To support evaluation, we introduce SafeVid, a novel AI-generated video detection benchmark comprising 20K videos spanning 10 social risk categories, designed to evaluate physical plausibility, structural consistency, and the rationality of social behaviors. Extensive experiments demonstrate the generalization of SafeGuard, improving accuracy on SafeVid by +18.7% and consistently outperforming prior methods across four public benchmarks.