FGAS uses adversarial perturbations and a fixed decoder network to hide messages in audio, reporting over 10 dB PSNR improvement and better anti-steganalysis than prior methods.
Audio steganog- raphy based on iterative adversarial attacks against con- volutional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FGAS: Fixed Decoder Network-Based Audio Steganography with Adversarial Perturbation Generation
FGAS uses adversarial perturbations and a fixed decoder network to hide messages in audio, reporting over 10 dB PSNR improvement and better anti-steganalysis than prior methods.