MMDStegNet: An Adversarial Steganography Framework with Maximum Mean Discrepancy Regularization

Ziwen He, Xingjie Dai, Xiang Zhang, Zhangjie Fu

Abstract: Recent advances in steganography leverage generative adversarial networks (GANs) as a robust framework for securing covert communications through adversarial training between stego-generators and steganalytic discriminators. This paradigm facilitates the synthesis of secure steganographic images by harnessing the competition between network components. However, existing GAN-based approaches suffer from asymmetric capacity between generators and discriminators: suboptimally trained discriminators provide inadequate gradient guidance for generator optimization, causing premature convergence and security degradation. To overcome this critical limitation, we propose an enhanced multi-steganalyzer adversarial architecture incorporating maximum mean discrepancy (MMD) regularization. Our framework introduces two key innovations: 1) an MMD-based regularization mechanism mitigating distributional discrepancies among multiple steganalyzers through kernel embedding optimization, and 2) a reward function with fusing gradients derived from multiple steganalyzers to boost reinforcement learning-based adversarial training. This dual strategy enables the discriminator to learn generalized forensic features while maintaining equilibrium in adversarial training dynamics, ultimately allowing the generator to produce stego images resistant to multiple steganalyzers simultaneously. Comprehensive experiments validate our method’s superiority: When evaluated across five steganalysis networks, including YedNet, CovNet, LWENet, SRNet, and SwT-SN, at 0.1-0.4 bpp payloads, the proposed framework achieves improvements in average detection error rates over state-of-the-art techniques such as SPAR-RL and GMAN. Ablation studies further confirm that MMD regularization contributes significantly to security enhancement.

External IDs:doi:10.1109/tcsvt.2025.3585589