ClusterMark applies visual token clustering to create robust in-generation watermarks for autoregressive image models, improving detectability under perturbations compared to direct token biasing while preserving quality.
Invisible image watermarks are provably removable using generative AI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering
ClusterMark applies visual token clustering to create robust in-generation watermarks for autoregressive image models, improving detectability under perturbations compared to direct token biasing while preserving quality.