用密钥控制的音频水印技术，解决版权保护难题。
WAKE: Watermarking Audio with Key Enrichment
- 通过密钥嵌入与解码，实现安全可控的水印
- 支持多次嵌入后仍可准确提取水印
- 可嵌入任意长度水印，适合版权追踪
随着深度学习在音频生成中的发展，音频安全与版权保护面临挑战，亟需鲁棒的音频水印技术。现有基于神经网络的方法虽有进展，但仍存在三大问题：防止未经授权访问、多次嵌入后无法解码初始水印、难以嵌入不同长度的水印。为此，我们提出 WAKE，首个密钥可控的音频水印框架。WAKE 使用特定密钥嵌入水印，并通过对应密钥恢复，错误密钥无法解码，显著提升安全性；通过设计机制避免水印被覆盖，支持多次嵌入后仍能正确提取；同时支持任意长度水印插入。WAKE 在水印音频质量与检测准确性上均优于现有模型。代码、更多结果及演示页面：https://thuhcsi.github.io/WAKE。
原文摘要 · Abstract (English)
As deep learning advances in audio generation, challenges in audio security and copyright protection highlight the need for robust audio watermarking. Recent neural network-based methods have made progress but still face three main issues: preventing unauthorized access, decoding initial watermarks after multiple embeddings, and embedding varying lengths of watermarks. To address these issues, we propose WAKE, the first key-controllable audio watermark framework. WAKE embeds watermarks using specific keys and recovers them with corresponding keys, enhancing security by making incorrect key decoding impossible. It also resolves the overwriting issue by allowing watermark decoding after multiple embeddings and supports variable-length watermark insertion. WAKE outperforms existing models in both watermarked audio quality and watermark detection accuracy. Code, more results, and demo page: https://thuhcsi.github.io/WAKE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。