# Moir'e Video Authentication: A Physical Signature Against AI Video Generation

arXiv: https://arxiv.org/abs/2604.01654 · HTML: https://mlsanity.com/paper/2604.01654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [Robust Invisible Video Watermarking with Attention](https://mlsanity.com/paper/1909.01285/) (2019)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [DeepFaceLab: Integrated, flexible and extensible face-swapping framework](https://mlsanity.com/paper/2005.05535/) (2020)
- [Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces](https://mlsanity.com/paper/2109.00162/) (2021)
- [Lighting (In)consistency of Paint by Text](https://mlsanity.com/paper/2207.13744/) (2022)
- [VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking](https://mlsanity.com/paper/2501.14195/) (2025)
- [AI-Generated Video Detection via Perceptual Straightening](https://mlsanity.com/paper/2507.00583/) (2025)
- [D3: Training-Free AI-Generated Video Detection Using Second-Order Features](https://mlsanity.com/paper/2508.00701/) (2025)
- [VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding](https://mlsanity.com/paper/2505.01481/) (2025)
- [Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection](https://mlsanity.com/paper/2510.08073/) (2025)
- [GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection](https://mlsanity.com/paper/2501.11340/) (2025)
- [Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content](https://mlsanity.com/paper/2412.12278/) (2024)
- [Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning](https://mlsanity.com/paper/2505.16836/) (2025)
- [Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook](https://mlsanity.com/paper/2411.19537/) (2024)
- [Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images](https://mlsanity.com/paper/2510.10231/) (2025)
- [Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks](https://mlsanity.com/paper/2109.09023/) (2021)
- [Combating Falsification of Speech Videos with Live Optical Signatures (Extended Version)](https://mlsanity.com/paper/2504.21846/) (2025)
- [Noise-Coded Illumination for Forensic and Photometric Video Analysis](https://mlsanity.com/paper/2507.23002/) (2025)

## Abstract (arXiv)

Recent advances in video generation have made AI-synthesized content increasingly difficult to distinguish from real footage. We propose a physics-based authentication signature that real cameras produce naturally, but that generative models cannot faithfully reproduce. Our approach exploits the Moir'e effect: the interference fringes formed when a camera views a compact two-layer grating structure. We derive the Moir'e motion invariant, showing that fringe phase and grating image displacement are linearly coupled by optical geometry, independent of viewing distance and grating structure. A verifier extracts both signals from video and tests their correlation. We validate the invariant on both real-captured and AI-generated videos from multiple state-of-the-art generators, and find that real and AI-generated videos produce significantly different correlation signatures, suggesting a robust means of differentiating them. Our work demonstrates that deterministic optical phenomena can serve as physically grounded, verifiable signatures against AI-generated video.