mAVE：面向联合音视频生成模型的水印框架

View PDF HTML (experimental)

Abstract:Watermarking joint audio-visual generation supports vendor copyright protection and content provenance. However, independently valid audio and video watermarks do not establish a shared generation session. An adversary can splice watermarked modalities from different sessions, causing the pair to be mistaken for the vendor's original joint output. We introduce mAVE (Manifold Audio-Visual Entanglement), a training-free watermarking framework that strengthens vendor attribution through session binding in native joint audio-visual diffusion transformers. mAVE separates public record retrieval from secret session authentication: a fixed public index locates the server record, while a randomized payload binds audio bits to a session-keyed video grid through a cryptographic digest. One prompt-conditioned joint inversion supports provider-assisted verification of both modalities against a session record, without modifying generator weights or training auxiliary watermark networks. Our analysis establishes implementation-matched distribution preservation and a full-initialization routing/clipping budget, alongside adaptive session-pool security and stable local-perturbation bounds. Experiments on LTX-2 and MOVA show comparable generation quality. mAVE achieves 99.8\% true-positive rate and 0\% observed false-positive rate in the evaluated swap test, and retains 99.2\% true-positive rate under FrameAvg temporal averaging. Same-prompt and similarity-selected swaps further test session authentication beyond perceptual compatibility.

Subjects:	Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2603.07090 [cs.CR]
	(or arXiv:2603.07090v2 [cs.CR] for this version)
	https://doi.org/10.48550/arXiv.2603.07090 arXiv-issued DOI via DataCite

Submission history

From: Luyang Si [view email]
[v1] Sat, 7 Mar 2026 07:59:31 UTC (12,388 KB)
[v2] Thu, 8 Oct 2026 05:04:14 UTC (12,412 KB)