CSF is the first black-box method to attribute fine-tuned text-to-image models to original lineages via compositional semantic probes and Bayesian decisions across multiple model families.
Attack-resilient image watermarking using stable diffusion.NeurIPS, 37: 38480–38507, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
CSF is the first black-box method to attribute fine-tuned text-to-image models to original lineages via compositional semantic probes and Bayesian decisions across multiple model families.