A curriculum-based loss scheduler for steganography trains first on embedding quality, then decoding, then steganalysis resistance, but its security gains are inconsistent across datasets.
Automatic steganographic distortion learning using a generative adversarial network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
TSCL:Multi-party loss Balancing scheme for deep learning Image steganography based on Curriculum learning
A curriculum-based loss scheduler for steganography trains first on embedding quality, then decoding, then steganalysis resistance, but its security gains are inconsistent across datasets.