2 papers
cs.SD2026
SSTMark: Robust Training-Free Semantic-Level Speech Watermarking
Kuan-Lin Chu, Jun-Cheng Chen, Chun-Shien Lu
As speech generation models become increasingly realistic and widely accessible, concerns about the misuse, attribution, and governance of synthetic speech continue to grow. Waterm…
cs.CR2026
Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective
Cheng-Yi Lee, Yichi Zhang, Yuchen Yang +2
Recent studies have shown that semantic watermarks, which embed information into the initial noise of latent diffusion models (LDMs), are vulnerable to black-box forgery attacks. H…