PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection

• URL: http://arxiv.org/abs/2609.15562v1
• Date: Mon, 14 Sep 2026 13:41:54 GMT
• Title: PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection
• Abstract summary: We introduce PIVOT, a physics-grounded AIGC detector, instantiated here for audio-video clips.<n>PIVOT estimates physical quantities from video and audio, selects physical laws relevant to each clip, and verifies their measurable constraints.<n>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.
• Score: 76.79584197983529
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• GEOPHYS: The Geometry of Physical Plausibility [80.0207225156318]
  We show that indicators of physical plausibility are implicitly captured by five geometric properties of the per-frame embeddings produced by frozen image encoders.<n>We robustly discriminates physically implausible videos from realistic ones, achieving state-of-the-art physics-violation detection.<n>Ultimately, GEOPHYS demonstrates that physical plausibility in videos can be assessed by leveraging the emergent geometric properties of temporal features extracted from image encoders.
  arXiv  Detail & Related papers  (2026-06-15T20:51:35Z)
• PhyGround: Benchmarking Physical Reasoning in Generative World Models [46.53245929361594]
  We introduce PhyGround, a criteria-grounded benchmark for evaluating physical reasoning in video generation.<n>The benchmark contains 250 curated prompts, each augmented with an expected physical outcome, and a taxonomy of 13 physical laws.<n>We evaluate eight modern video generation models through a large-scale, quality-controlled human study.
  arXiv  Detail & Related papers  (2026-05-11T16:30:51Z)
• Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification [4.2958409172092225]
  Mobile remote identity verification (RIdV) systems are exposed to attacks that manipulate or replace the facial video stream.<n>Recent European requirements, including ETSI TS 119 461 and CEN/TS 18099, motivate complementary evidence channels beyond camera-based presentation-attack detection.<n>This paper investigates whether passive motion traces recorded during selfie capture provide auxiliary evidence for spoof screening and user verification.
  arXiv  Detail & Related papers  (2026-04-30T20:46:18Z)
• PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation [63.3417467957431]
  Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content.<n>We present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to evaluate the audio physics grounding capabilities of existing T2AV models.<n>Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation.
  arXiv  Detail & Related papers  (2025-12-30T05:22:31Z)
• Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning [66.51617619673587]
  We present Skyra, a specialized large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos.<n>To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video dataset with fine-grained human annotations.<n>We then develop a two-stage training strategy that systematically enhances our model's artifact's-temporal perception, explanation capability, and detection accuracy.
  arXiv  Detail & Related papers  (2025-12-17T18:48:26Z)
• PAVAS: Physics-Aware Video-to-Audio Synthesis [58.746986798623084]
  We present Physics-Aware Video-to-Audio Synthesis (PAVAS), a method that incorporates physical reasoning into a latent diffusion-based V2A generation.<n>We show that PAVAS produces physically plausible and perceptually coherent audio, outperforming existing V2A models in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-12-09T06:28:50Z)
• AI-Generated Video Detection via Perceptual Straightening [10.189379841180285]
  We propose ReStraV, a novel approach to distinguish natural from AI-generated videos.<n>Inspired by the "perceptual straightening" hypothesis, we quantify the temporal curvature and stepwise distance in the model's representation domain.<n>Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos.
  arXiv  Detail & Related papers  (2025-07-01T09:04:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.