PIVOT：基于物理验证的AI生成音视频检测
PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection
- Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
- Nanjing University of Posts and Telecommunications（南京邮电大学）
- University at Buffalo, State University of New York（纽约州立大学布法罗分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
PIVOT提出基于物理定律验证音视频事件约束的AIGC检测方法，在PhysForensics-Bench上显著优于直接检查，提供可解释证据。
AI中文摘要：
随着生成模型的不断进步，AI生成内容（AIGC）变得越来越逼真，削弱了现有检测器常用的伪影线索。然而，忠实地再现真实世界事件的物理行为对当前生成器而言仍具挑战性。因此，我们探索通过评估所描绘事件是否满足源自物理定律的可测量约束来检测AIGC。我们提出了PIVOT，一种基于物理的AIGC检测器，此处针对音视频片段实例化，它从视频和音频中估计物理量，选择与每个片段相关的物理定律，并验证其可测量约束。除了真实/虚假的判定外，PIVOT还返回支持性证据，记录每个适用定律的验证结果、相关时间窗口和支持量。尽管此处仅在音视频数据上实例化和评估，但该框架原则上可扩展到其他AIGC模态，只要验证所需的物理量能被可靠估计。我们还引入了PhysForensics-Bench，包含来自九个事件中心场景族和两个近期音视频生成器的成对真实与生成音视频片段。在PhysForensics-Bench上，PIVOT在Real+Seedance上达到70.30%的准确率和64.29%的F1分数，在Real+VEO上达到72.16%的准确率和65.82%的F1分数。相比之下，使用Gemini 3.1 Pro直接检查在Real+Seedance上获得53.96%的准确率和60.09%的F1分数，在Real+Veo上获得57.22%的准确率和63.44%的F1分数。这些结果证明了物理一致性验证作为一种结构化且可检查的证据来源的实际前景，可补充基于伪影的AIGC检测。
英文摘要：
As generative models continue to advance, AI-generated content (AIGC) is becoming increasingly realistic, weakening the artifact cues commonly exploited by existing detectors. Nevertheless, faithfully reproducing the physical behavior of real-world events remains challenging for current generators. We therefore explore detecting AIGC by assessing whether the depicted event satisfies measurable constraints derived from physical laws. We introduce PIVOT, a physics-grounded AIGC detector, instantiated here for audio-video clips, that estimates physical quantities from video and audio, selects physical laws relevant to each clip, and verifies their measurable constraints. Beyond a real/fake decision, PIVOT returns supporting evidence that records the verification outcome, relevant time window, and supporting quantities for each applicable law. Although instantiated and evaluated here on audio-video data, the framework can, in principle, extend to other AIGC modalities whenever the physical quantities required for verification can be estimated reliably. We also introduce PhysForensics-Bench, comprising paired real and generated audio-video clips from nine event-centric scene families and two recent audio-video generators. On PhysForensics-Bench, PIVOT achieves 70.30% accuracy and 64.29% F1 score on Real+Seedance, and 72.16% accuracy and 65.82% F1 on Real+VEO. In comparison, direct inspection with Gemini 3.1 Pro obtains 53.96% accuracy and 60.09% F1 on Real+Seedance, and 57.22% accuracy and 63.44% F1 on Real+Veo. These results demonstrate the practical promise of physical-consistency verification as a structured and inspectable source of evidence that complements artifact-based AIGC detection.
