AI造假视频,查得出还说得清
检测 AI 生成视频的旧办法,要么让模型一口气想完、漏掉一闪而过的破绽,要么按固定流程走、不会随机应变。这篇让一个「主调查员」带着一支会自己进化的取证小队,画面和声音的线索分头查:主调查员决定查哪种痕迹、看哪一段、什么时候收手,查到的结果同时喂回给两层——主调查员学得快,取证员改得慢,慢慢把以前被忽略的细微痕迹也认出来。在域内、域外和智能体三类评测上平均 95.2% 准确率,比此前最强检测器高 9.0%,而且每个结论都落在具体某段画面或声音上,不是只给一个真假。它不是你明天能用上的工具,但「判定要带证据」这条,是以后平台给视频打真假标签时绕不开的方向。
📄 原文摘要(英文)
Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeVisForensics, an agentic framework in which a main investigator agent coordinates a self-evolving library of forensic inspector sub-agents spanning visual and audio cues. The investigator learns which artifact type to examine, over which window, and when to conclude, and these interactions provide shared feedback for both levels of agents. Our dual-timescale policy optimization strategy, DTPO, closes this loop through fast reinforcement learning of the investigator and slower refinement of the inspectors, guided by annotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curate ForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanying reinforcement-learning pool. Experiments show that WeVisForensics averages 95.2% detection accuracy across in-domain, out-of-domain and agentic benchmarks, 9.0% above the strongest prior detector, while grounding its verdicts in localized evidence.