today local_bar

Kai Ye

PhD student, University of Hong Kong

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

#1401 · Zhisheng Zhang, Derui Wang, Yifan Mi, Zhiyong Wu, JieGao, Yuxin Cao, Kai Ye, Jason Xue, Jie Hao

We propose a proactive defensive framework against malicious production LLM-based speech synthesis to protect our voice information.