用多重水印技术提升语音防伪抗攻击能力
Multiplexing Neural Audio Watermarks
- 融合多种水印方法，通过时频域自适应设计增强鲁棒性
- 在14种攻击下性能显著优于单一水印方案，抗干扰能力更强
- 适合语音版权保护与真实场景中的防伪造应用
语音水印对验证语音真实性至关重要，但传统单水印方案在神经重建和对抗攻击等复杂干扰下表现不佳。为此，本文提出多路复用范式，结合多种水印技术以利用其互补优势。研究了并行与串行两种复用策略，提出感知自适应时频复用（PA-TFM），一种无需训练的鲁棒方法。为进一步提升性能，引入基于模型的MaskNet框架，用于学习有效时域复用。在LibriSpeech与Common Voice数据集上，针对14种不同攻击类型（包括高强度白盒攻击与神经重建攻击）的实验表明，PA-TFM与MaskNet均显著优于现有单水印基线，建立起适用于真实场景的强健语音保护范式。
原文摘要 · Abstract (English)
Audio watermarking is essential for verifying speech authenticity, yet single-watermark schemes often struggle against sophisticated distortions such as neural reconstruction and adversarial attacks. To address this limitation, we introduce a multiplexing paradigm that combines multiple watermarking techniques to leverage their inherent complementarities. We explore both parallel and sequential multiplexing strategies and propose perceptual-adaptive time-frequency multiplexing (PA-TFM), a robust training-free approach. To further enhance performance, we introduce MaskNet, a novel model-based framework designed to learn effective time-domain multiplexing. Experimental results on the LibriSpeech and Common Voice datasets under 14 diverse attack types, including high-strength white-box and neural reconstruction attacks, demonstrate that both PA-TFM and MaskNet considerably outperform existing single-watermark baselines, establishing a resilient paradigm for real-world audio protection.
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。