Presents dynamics-level watermarking for flow matching models via random coding over continuous channels, embedding key-dependent perturbations in the velocity field that preserve the generated distribution and enable black-box message recovery.
Foundations of Physics , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
Presents dynamics-level watermarking for flow matching models via random coding over continuous channels, embedding key-dependent perturbations in the velocity field that preserve the generated distribution and enable black-box message recovery.