AI Research

Dynamics-Level Watermarking of Flow Matching Models with Random Codes

Medium Severity Global
Date Occurred May 15, 2026 17:48 UTC
Event Type AI Research
Source arXiv
Recorded May 18, 2026
Full Description

arXiv: Dynamics-Level Watermarking of Flow Matching Models with Random Codes We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the watermark directly into the learned continuous dynamics -- the velocity field of a flow matching model. We formulate this as random coding over a continuous channel: a key-dependent perturbation is added during training, and the message is recovered at detection time from black-box queries. The perturbation is designed to leave the generated distribu

AI Intelligence Layer

AI Categories

performance
Event Metadata
  • ID #1873
  • Type AI Research
  • Region Global
  • Severity Medium
  • Indexed May 18, 2026