用少量无标签数据模拟未知图像处理流程，提升隐写分析鲁棒性。
Tackle CSM in JPEG Steganalysis with Data Adaptation
- 从少量无标签目标数据中学习未知处理流程，构建图像模拟器。
- 在真实和模拟场景下显著提升对覆盖源不匹配的鲁棒性。
- 适合缺乏标注数据且处理流程未知的隐写分析实战场景。
隐写分析模型在基准数据集上表现优异，但在真实场景中面对训练时未见的图像处理流水线时性能下降，这一问题称为覆盖源不匹配（CSM）。在实际应用中，从业者通常仅拥有少量无标签数据，不清楚具体使用了哪些处理技术，也缺乏覆盖图像与隐写图像的比例信息。为此，本文提出TADA（目标对齐的数据适配），一种通过小规模无标签目标集学习未知处理流程的框架。该架构采用残差协方差对齐、残差分布匹配及ℓ²损失联合训练，使模拟器生成逼真的图像。在模拟和真实目标上，TADA相比强基线方法显著提升了对CSM的鲁棒性和操作泛化能力。更多资源见：https://github.com/RonyAbecidan/TADA
原文摘要 · Abstract (English)
Steganalysis models excel on benchmark datasets but struggle in the wild when analyzed images are produced by a processing pipeline unseen during training. This problem known as Cover Source Mismatch (CSM) is particularly hard in realistic settings where practitioners (1) have access to only a small, unlabeled dataset, (2) are unsure of the processing techniques applied to these images, and (3) lack information on the proportion of covers and stegos in that set. To answer this challenge, we introduce TADA (Target Alignment through Data Adaptation), a framework learning to emulate the unknown processing pipeline from a small unlabeled target set. This architecture is trained with a loss combining residual covariance alignment, residual distribution matching, and a $\ell^2$ loss constraining the emulator to produce realistic images. Across toy and operational targets, TADA yields substantial gains in robustness to CSM and improves operational generalization compared to strong holistic and atomistic baselines. Additional resources are available at this link: https://github.com/RonyAbecidan/TADA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。