paper-with-me

Papers

CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning

2025-05-25 · Renyuan Li, Zhibo Liang, Haichuan Zhang, Tianyu Shi, Zhiyuan Cheng, Jia Shi, Carl Yang, Mingjie Tang

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).

📄 PDF Abstract BibTeX arXiv:2505.19119

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to SpeechVoice Cloning

Methods 이 논문이 사용한 방법론

SRS Sticker Response Selector, or SRS, is a model for multi-turn dialog that automatically selects a sticker response. SRS first employs a convolutional based sticker image…

Similar Papers 제목 키워드 기반

Defending Against Universal Perturbations With Shared Adversarial Training

2018-12-10 · ICCV 2019 10 · Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image class…

image-classificationImage ClassificationSemantic Segmentation

UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

2022-07-05 · Hanbin Hong, Binghui Wang, Yuan Hong

We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate …

Watertox: The Art of Simplicity in Universal Attacks A Cross-Model Framework for Robust Adversarial Generation

2024-12-20 · Zhenghao Gao, Shengjie Xu, Meixi Chen, Fangyao Zhao

Contemporary adversarial attack methods face significant limitations in cross-model transferability and practical applicability. We present Watertox, an elegant adversarial attack framework achieving remarkable effective…

Adversarial AttackDiversity

Defense against Universal Adversarial Perturbations

2017-11-16 · CVPR 2018 6 · Naveed Akhtar, Jian Liu, Ajmal Mian

Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to `any' image can fool a state-of-the-art network classifier to change its prediction about the i…

Defending Against Universal Attacks Through Selective Feature Regeneration

2019-06-08 · CVPR 2020 6 · Tejas Borkar, Felix Heide, Lina Karam

Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, image-agnostic (universal adversarial) perturbations added to any image can fool a targ…

Adversarial Defense