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

arXiv: https://arxiv.org/abs/2609.15562 · HTML: https://mlsanity.com/paper/2609.15562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 60 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 30 of 49)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [Track Anything: Segment Anything Meets Videos](https://mlsanity.com/paper/2304.11968/) (2023)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [Decoupling Features in Hierarchical Propagation for Video Object Segmentation](https://mlsanity.com/paper/2210.09782/) (2022)
- [PHYRE: A New Benchmark for Physical Reasoning](https://mlsanity.com/paper/1908.05656/) (2019)
- [Visually Indicated Sounds](https://mlsanity.com/paper/1512.08512/) (2015)
- [FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation](https://mlsanity.com/paper/2311.01813/) (2023)

## Abstract (arXiv)

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.