arXiv：cs.AI· Luyang Si, Leyi Pan, Dongsheng Ma, Lijie Wen·· 3 小时前
mAVE：面向联合音视频生成模型的会话绑定水印框架
mAVE: A Watermark for Joint Audio-Visual Generation Models
AI 导读
研究者提出免训练水印框架 mAVE，通过会话绑定为原生联合音视频扩散 Transformer 提供厂商归属认证。mAVE 将公开记录检索与密钥会话认证分离，用随机载荷将音频比特经密码摘要绑定到会话密钥视频网格，单次提示词条件联合反演即可验证两模态。在 LTX-2 和 MOVA 上，其换位测试真阳性率达 99.8%、假阳性率 0%，FrameAvg 时间平均下仍保留 99.2% 真阳性率。
正文
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)
来源：arXiv：cs.AI · arxiv.org