arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.05310cs.SDcs.AI
收藏

Latent-Mark: 一种对神经编解码器压缩鲁棒的音频水印

Latent-Mark: An Audio Watermark Robust to Neural Codec Compression

Yen-Shan Chen, Shih-Yu Lai, Ying-Jung Tsou, Yi-Cheng Lin, Bing-Yu Chen, Yun-Nung Chen, Hung-yi Lee, Shang-Tse Chen

AI总结:

针对神经音频编解码器压缩导致现有水印失效的问题,提出Latent-Mark,首个在编解码器不变潜空间嵌入水印的零比特音频水印框架,通过优化波形诱导潜表示方向偏移并引入跨编解码器优化,实现鲁棒零样本迁移。

摘要:

虽然现有的音频水印技术已经对传统数字信号处理攻击具有强鲁棒性,但它们仍然容易受到神经压缩的影响。这是因为现代神经音频编解码器充当噪声滤波器,丢弃了先前水印方法中使用的不可察觉的波形变化。为了解决这一限制,我们提出了Latent-Mark,这是第一个旨在抵御神经编解码器压缩的零比特音频水印框架。我们的关键见解是,对编码-解码过程的鲁棒性需要将水印嵌入到编解码器的不变潜空间中。我们通过优化音频波形以在其编码的潜表示中引起可检测的方向偏移来实现这一点,同时约束扰动以对齐自然音频流形,从而确保不可感知性。为了防止过度拟合单个编解码器的量化规则,我们引入了跨编解码器优化,联合优化多个替代编解码器上的波形以针对共享的潜不变量。广泛的评估表明,对未见过的神经编解码器具有鲁棒的零样本迁移能力,在保持感知不可感知性的同时,实现了对传统DSP攻击的竞争性鲁棒性。我们希望我们的工作能够激发未来对通用水印框架的研究,这些框架能够在日益复杂和多样化的生成失真中保持完整性。

英文摘要:

While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural compression. This occurs because modern neural audio codecs act as noise filters and discard the imperceptible waveform variations used in prior watermarking methods. To address this limitation, we propose Latent-Mark, the first zero-bit audio watermarking framework designed to survive neural codec compression. Our key insight is that robustness to the encode-decode process requires embedding the watermark within the codec's invariant latent space. We achieve this by optimizing the audio waveform to induce a detectable directional shift in its encoded latent representation, while constraining perturbations to align with the natural audio manifold to ensure imperceptibility. To prevent overfitting to a single codec's quantization rules, we introduce Cross-Codec Optimization, jointly optimizing the waveform across multiple surrogate codecs to target shared latent invariants. Extensive evaluations demonstrate robust zero-shot transferability to unseen neural codecs, achieving competitive resilience against traditional DSP attacks while preserving perceptual imperceptibility. We hope our work will inspire future research into universal watermarking frameworks capable of maintaining integrity across increasingly complex and diverse generative distortions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑