CloneShield：针对零样本语音克隆的通用扰动框架
CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning
AI总结：
针对零样本语音克隆的隐私威胁，提出CloneShield通用时域对抗扰动框架，通过多目标优化和梅尔频谱分解实现跨说话人与话语的鲁棒防御，在保持音频质量的同时显著降质克隆输出。
摘要：
近期文本到语音（TTS）语音克隆技术的突破引发了严重的隐私担忧，该技术仅需几秒钟的参考音频即可实现高度准确的声纹身份复制，同时保留说话人的声音真实性。本文提出CloneShield，一种专门用于防御零样本语音克隆的通用时域对抗扰动框架。我们的方法提供跨说话人和话语的鲁棒保护，且无需任何关于合成文本的先验知识。我们将扰动生成建模为多目标优化问题，并提出多梯度下降算法（MGDA）以确保跨多样话语的鲁棒保护。为保持用户自然的听觉感知，我们通过梅尔频谱图表示分解对抗扰动，并针对每个样本进行微调。该设计在保持不可感知性的同时，对零样本克隆输出产生强烈的降质效果。在三个最先进的零样本TTS系统、五个基准数据集以及60名人类听者的评估上的实验表明，我们的方法在受保护输入中保持接近原始的音频质量（PESQ = 3.90，SRS = 0.93），同时大幅降低克隆样本的说话人相似度和语音质量（PESQ = 1.07，SRS = 0.08）。
英文摘要：
Recent breakthroughs in text-to-speech (TTS) voice cloning have raised serious privacy concerns, allowing highly accurate vocal identity replication from just a few seconds of reference audio, while retaining the speaker's vocal authenticity. In this paper, we introduce CloneShield, a universal time-domain adversarial perturbation framework specifically designed to defend against zero-shot voice cloning. Our method provides protection that is robust across speakers and utterances, without requiring any prior knowledge of the synthesized text. We formulate perturbation generation as a multi-objective optimization problem, and propose Multi-Gradient Descent Algorithm (MGDA) to ensure the robust protection across diverse utterances. To preserve natural auditory perception for users, we decompose the adversarial perturbation via Mel-spectrogram representations and fine-tune it for each sample. This design ensures imperceptibility while maintaining strong degradation effects on zero-shot cloned outputs. Experiments on three state-of-the-art zero-shot TTS systems, five benchmark datasets and evaluations from 60 human listeners demonstrate that our method preserves near-original audio quality in protected inputs (PESQ = 3.90, SRS = 0.93) while substantially degrading both speaker similarity and speech quality in cloned samples (PESQ = 1.07, SRS = 0.08).
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。
