<ul data-eligibleForWebStory="false"><li>Speech synthesis advancements have raised concerns about voice cloning attacks despite existing protective perturbations.</li><li>While previous studies focused on disrupting voice cloning with perturbations, determined attackers could overcome these defenses.</li><li>A new study evaluates protective perturbations against voice cloning with perturbation purification, showcasing limitations in current methods.</li><li>A novel two-stage purification method, including phoneme guidance, demonstrates improved disruption of voice cloning defenses.</li></ul>

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks

Discover more