Image Steganography With Dual Strategies: Defense and Attack

Zhecong Ren, Wei Guo, Chang Lin, Haibo Jin, Haicheng Qu

Abstract: This letter addresses the limitations of adversarial steganography, such as inadequate cross-model generalization capability and suboptimal stego image quality, by proposing a dual-strategy steganography framework that combines passive defense with active attack. The passive defense module utilizes a generative adversarial network, wherein the generator adopts a dual-stream U-Net architecture to analyze the cover image alongside its edge information. It incorporates a Convolutional Block Attention Module to dynamically assign feature weights, resulting in an optimized cover image for information embedding. The active attack module identifies and interferes with the essential shared features that different steganalysis models depend on for discrimination, utilizing neuron attribution results. This approach optimizes the embedding scheme in a specific manner, leading various steganalysis models to arrive at erroneous conclusions. The dynamic adjustment of loss weight progressively enhances the performance of both modules, leading to overall optimization. Experimental results indicate that the proposed framework successfully achieves a balance between high visual quality and strong cross-model generalization capability.