发表机构
Qilu University of Technology (Shandong Academy of Sciences); Shandong Computer Science Center; Shandong Fundamental Research Center for Computer Science（齐鲁工业大学（山东省科学院）; 山东省计算中心; 山东省计算机科学基础研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出StyleStegaNet，通过风格化传输替代封面匹配，实现行为级伪装的图像隐写，并采用四阶段解耦与渐进训练，在DIV2K和MS-COCO上验证有效性，检测准确率仅约51%。
AI 中文摘要
图像隐写术将秘密信息隐藏在正常图像中，现有的大多数方法依赖于保持封面（cover）的传输。然而，一旦原始封面被暴露或能被可靠地近似，这种范式就会变得脆弱。在本文中，我们提出StyleStegaNet，一种风格化图像隐藏框架，用风格隐藏传输取代封面匹配。StyleStegaNet不传输类似封面的隐写图像，而是基于公开可用的风格参考生成风格化的隐写图像，将隐写术的不可见性从保持封面的隐藏重新定义为基于风格转换的行为级伪装。这种设置对可靠的秘密恢复构成了重大挑战，因为神经风格化可以显著改变深度隐藏方法所利用的特征统计。为了应对这一挑战，StyleStegaNet将整体任务解耦为四个协调阶段：隐写生成、风格化传输、结构保持重建和秘密恢复。此外，StyleStegaNet采用渐进式三阶段训练策略进行优化，其中小波域约束和感知监督引导可恢复信息朝向结构表示。我们进一步提供分析表明，秘密可恢复性主要限于归一化结构子空间，这为直接风格化基线失败的原因以及为什么需要重建引导的恢复路径提供了机制性解释。在DIV2K和MS-COCO数据集上的大量实验证明了StyleStegaNet的有效性。使用两个深度检测器进行的少样本图像隐写分析进一步显示检测准确率接近随机猜测，约为51%。
英文摘要
Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a paradigm becomes vulnerable once the original cover is exposed or can be reliably approximated. In this paper, we propose StyleStegaNet, a stylized image hiding framework that replaces cover matching with style-concealment transmission. Instead of transmitting a cover-like stego image, StyleStegaNet generates stylized stego images conditioned on publicly available style references, redefining steganography invisibility from cover-preserving concealment to behavior-level camouflage based on style transformation. Such a setting poses a substantial challenge to reliable secret recovery, since neural stylization can significantly alter the feature statistics exploited by deep hiding methods. To address this challenge, StyleStegaNet decouples the overall task into four coordinated stages: stego generation, stylized transmission, structure-preserving reconstruction, and secret recovery. Moreover, StyleStegaNet is optimized with a progressive three-stage training strategy, in which wavelet-domain constraints and perceptual supervision guide the recoverable information toward structural representations. We further provide an analysis showing that secret recoverability is largely restricted to the normalized structural subspace, offering a mechanistic explanation for why directly stylized baselines fail and why a reconstruction-guided recovery path is necessary. Extensive experiments on DIV2K and MS-COCO datasets demonstrate the effectiveness of StyleStegaNet. And few-shot image steganalysis with two deep detectors further shows detection accuracy near random guessing, approximately 51\%.
Comments17 pages, 7 figures, 5 tables
