Problem
Research questions and friction points this paper is trying to address.
AI video generation
video authentication
Moiré effect
deepfake detection
physical signature
Moiré Video Authentication: A Physical Signature Against AI Video Generation
🤖 AI Summary
This work addresses the growing challenge of verifying the authenticity of increasingly realistic AI-generated videos by proposing a physics-based authentication method rooted in the moiré effect. The authors observe that when a real camera captures images of dual-layer gratings, it produces characteristic interference patterns that current AI models fail to accurately reproduce due to their inability to simulate this physical phenomenon. By establishing an optical geometric model, the study reveals a linear coupling relationship between moiré fringe phase and grating displacement, enabling the derivation of a moiré motion invariant. This invariant is independent of both camera-to-object distance and specific grating structures, offering a universal basis for authenticity verification. Experimental results demonstrate that the proposed algorithm effectively distinguishes between real and AI-generated videos across multiple state-of-the-art generative models with high accuracy.
📝 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 Moiré effect: the interference fringes formed when a camera views a compact two-layer grating structure. We derive the Moiré 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Moiré effect
video authentication
AI-generated video detection
physical signature
motion invariant
🔎 Similar Papers
No similar papers found.
