VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning

TL;DR

VoiceCloak is a comprehensive defense framework that employs adversarial perturbations and disruption of diffusion model processes to prevent unauthorized voice cloning, addressing the unique challenges posed by diffusion-based generative mechanisms.

Contribution

It introduces a novel multi-dimensional proactive defense specifically designed for diffusion models in voice cloning, disrupting both speaker identity and output quality.

Findings

High defense success rate against diffusion-based voice cloning

Effective obfuscation of speaker identity and degradation of speech quality

Demonstrated robustness across various experimental scenarios

Abstract

Diffusion Models (DMs) have achieved remarkable success in realistic voice cloning (VC), while they also increase the risk of malicious misuse. Existing proactive defenses designed for traditional VC models aim to disrupt the forgery process, but they have been proven incompatible with DMs due to the intricate generative mechanisms of diffusion. To bridge this gap, we introduce VoiceCloak, a multi-dimensional proactive defense framework with the goal of obfuscating speaker identity and degrading perceptual quality in potential unauthorized VC. To achieve these goals, we conduct a focused analysis to identify specific vulnerabilities within DMs, allowing VoiceCloak to disrupt the cloning process by introducing adversarial perturbations into the reference audio. Specifically, to obfuscate speaker identity, VoiceCloak first targets speaker identity by distorting representation learning embeddings to maximize identity variation, which is guided by auditory perception principles. Additionally, VoiceCloak disrupts crucial conditional guidance processes, particularly attention context, thereby preventing the alignment of vocal characteristics that are essential for achieving convincing cloning. Then, to address the second objective, VoiceCloak introduces score magnitude amplification to actively steer the reverse trajectory away from the generation of high-quality speech. Noise-guided semantic corruption is further employed to disrupt structural speech semantics captured by DMs, degrading output quality. Extensive experiments highlight VoiceCloak's outstanding defense success rate against unauthorized diffusion-based voice cloning. Audio samples of VoiceCloak are available at https://voice-cloak.github.io/VoiceCloak/.