AI RESEARCH
Latent-Mark: An Audio Watermark Robust to Neural Resynthesis
arXiv CS.AI
•
ArXi:2603.05310v2 Announce Type: replace-cross While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural resynthesis. This occurs because modern neural audio codecs act as semantic filters and discard the imperceptible waveform variations used in prior watermarking methods. To address this limitation, we propose Latent-Mark, the first zero-bit audio watermarking framework designed to survive semantic compression.