Qianyue Hu

VoiceCloak: A Multi-Dimensional Defense Framework Against Unauthorized Diffusion-Based Voice Cloning

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 t