Hai-Xia Wang

Cost-Guided Joint Mask-Perturbation Optimization with Attentive Decoding for Image Steganography

This paper proposes a cost-guided joint mask–perturbation optimization with attentive decoding for image steganography method (CMAD), which jointly optimizes the embedding mask, perturbation magnitude, and decoding-network parameters, thereby improving recovery accuracy while preserving imperceptibility.