SEAL uses semantic embeddings and locality-sensitive hashing to create distortion-free, database-free watermarks for generative images that are conditioned on content for improved forgery resistance.
Black-box forgery attacks on seman- tic watermarks for diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SEAL: Semantic Aware Image Watermarking
SEAL uses semantic embeddings and locality-sensitive hashing to create distortion-free, database-free watermarks for generative images that are conditioned on content for improved forgery resistance.