AI Paper Atlas

Research map / Video / Video-language understanding

SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection

Wenlin Wu, Sheng Zhou, Peipei Song, Wenhao Wang, Junbin Xiao, Xun Yang

ECCV 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add social risk-aware hypothesis generation and routing (SHGR) to GPT-4o (ablation)GPT-4o baseline · Overall Avgaccuracy (%): 66.8 -> 68.5Improved
add video cropping (VC) after SHGR (ablation)GPT-4o + SHGR · Overall Avgaccuracy (%): 68.5 -> 72.4Improved
add forensic trace extraction (FTE) after SHGR+VC (ablation)GPT-4o + SHGR + VC · Overall Avgaccuracy (%): 72.4 -> 84.1Improved
add self-reflective verifier (SRV) to SHGR+VC+FTE (ablation)GPT-4o + SHGR + VC + FTE · Overall Avgaccuracy (%): 84.1 -> 89.3Improved
add SRV without FTE (SHGR+VC) (ablation)GPT-4o + SHGR + VC · Overall Avgaccuracy (%): 72.4 -> 81.8Improved
add SRV without FTE (SHGR+VC) on SafeVid F1 is a minor gain (ablation)GPT-4o + SHGR + VC · SafeVid AvgF1 (%): 71.0 -> 71.8Improved
add SHGR alone on SafeVid F1 (ablation)GPT-4o baseline · SafeVid AvgF1 (%): 60.5 -> 59.1Hurt
add optical-flow tool to SRV-only variant (w/o tool use) (ablation)SafeGuard · Overall Avgaccuracy (%): 81.8 -> 83.0Improved
add depth tool to optical flow (ablation)SafeGuard · Overall Avgaccuracy (%): 83.0 -> 85.0Improved
add appearance tool (ablation)SafeGuard · Overall Avgaccuracy (%): 85.0 -> 88.0Improved
add pixel-level tool (ablation)SafeGuard · Overall Avgaccuracy (%): 88.0 -> 89.3Improved
use SafeGuard over plain GPT-4o on out-of-domain SafeVidGPT-4o · SafeVid OODaccuracy (%): 63.7 -> 80.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy