UnVC: Protecting Your Voiceprint by Generative Adversarial Speech

Summary

This paper proposes UnVC (Unable to be Voice Cloned), a proactive defense against malicious voice cloning that uses a WaveGlow-based generative adversarial speech approach to produce distribution-consistent anti-fake speech samples instead of adding perturbations to the original signal. The authors report that UnVC outperforms existing mainstream methods in robustness, generalization to unseen cloning attacks, and anti-fake sample quality, and that it keeps reliable anti-fake capability under social media and re-recording conditions.

Related items

• MediumCVE-2026-126994: braindecode model config deserialization flaw via activation argumentSimilar attack · NVD/CVE Database
• MediumAI found Linux kernel bugs that remained undetected for decadesSimilar attack · CSO Online
• InfoInside an AI Attack Against a US RetailerSimilar attack · Dark Reading
• HighCVE-2026-67547: taOS remote code execution via skill-exec endpoint for non-admin usersSimilar attack · NVD/CVE Database
• MediumCVE-2026-65957: Helio dashboard CORS origin validation bypass via private-network prefix matchSimilar attack · NVD/CVE Database