AI 能听出视频被改过，但说不出来
现在的 AI 检测视频造假，基本只看画面，而且只适合短视频。这篇把检测拉长到 998 小时的视频，还同时看画面和声音：一段视频里可能只有几秒被改过，AI 要能指出具体是哪几秒、改的是画面还是声音。结果很有意思：让大模型直接回答，它几乎猜不中；但把模型内部感知层单独接出来，它其实早就发现了问题——证据在，只是说不出口。这提醒我们，AI 的「判断」和「表达」是两回事，别因为它说不出来就以为它不知道。
📄 原文摘要(英文)
Localized AI manipulations in long-form videos often affect brief events within otherwise authentic content, making video-level classification insufficient for forensic analysis. Existing audio-visual deepfake benchmarks largely focus on short talking-head clips, while long-form temporal forensics remains predominantly visual. We introduce AV-FABLE, a dual-timeline benchmark for sparse manipulations in open-scene long-form audio-visual videos. AV-FABLE contains 16,650 pristine--manipulated twin pairs (998 hours) created with 27 editing configurations, with separate audio and visual timelines that enable modality-specific temporal localization and expose errors hidden by joint-timeline evaluation. On AV-FABLE, zero-shot prompting of audio-visual large language models (AV-LLMs) yields near-chance detection and poor temporal localization. In contrast, supervised readouts of their frozen perception features recover strong forensic signals, suggesting manipulation evidence is encoded in these representations but not effectively exposed through language outputs. Motivated by this observation, we propose NFSR(Native Forensics via Separated Readouts), which reads frozen AV-LLM features with separate audio and visual temporal decoders. NFSR achieves the best audio-visual localization performance in-domain and across all three out-of-distribution settings, including transfer to held-out videos from an external long-video forensic benchmark. AV-FABLE, code, and model weights will be publicly released.