GIFDL trains a GAN-based steganographic distortion model with fluctuation images from a text-to-image generator, raising steganalysis detection error by an average of 3.30% over the GMAN baseline.
A new cost function for spatial image steganography,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GIFDL: Generated Image Fluctuation Distortion Learning for Enhancing Steganographic Security
GIFDL trains a GAN-based steganographic distortion model with fluctuation images from a text-to-image generator, raising steganalysis detection error by an average of 3.30% over the GMAN baseline.