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

arXiv cs.CV / 4/3/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a physics-based “Moiré” authentication signature that real cameras naturally produce but generative video models struggle to replicate faithfully.
It leverages interference fringes from a compact two-layer grating, deriving a Moiré motion invariant that linearly couples fringe phase and grating displacement based on optical geometry (largely independent of viewing distance and grating details).
A verifier extracts both signals from a video and checks their correlation to decide whether the footage is real-captured or AI-generated.
Experiments validate the invariant across real-captured videos and multiple state-of-the-art AI generator outputs, finding significantly different correlation signatures between the two.
The work argues that deterministic optical phenomena can provide a physically grounded, verifiable method for detecting AI-synthesized videos.

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 robust means of differentiating them. Our work demonstrates that deterministic optical phenomena can serve as physically grounded, verifiable signatures against AI-generated video.