Moir\'e Video Authentication: A Physical Signature Against AI Video Generation
Yuan Qing, Kunyu Zheng, Lingxiao Li, Boqing Gong, Chang Xiao

TL;DR
This paper introduces a physics-based Moiré effect signature that distinguishes real videos from AI-generated ones by exploiting interference patterns that generative models cannot replicate.
Contribution
It derives a Moiré motion invariant linking fringe phase and image displacement, enabling robust differentiation between real and AI-generated videos.
Findings
Real videos show strong correlation signatures; AI videos do not.
The invariant is independent of viewing distance and grating structure.
Validation across multiple AI generators confirms robustness.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
