Recent research has shown that non-additive image steganographic frameworks effectively improve security performance through adjusting distortion distribution. However, as far as we know, all of the existing non-additive proposals are based on handcrafted policies, and can only be applied to a specific image domain, which heavily prevent non-additive steganography from releasing its full potentiality. In this paper, we propose an automatic non-additive steganographic distortion learning framework called MCTSteg to remove the above restrictions. Guided by the reinforcement learning paradigm, we combine Monte Carlo Tree Search (MCTS) and steganalyzer-based environmental model to build MCTSteg. MCTS makes sequential decisions to adjust distortion distribution without human intervention. Our proposed environmental model is used to obtain feedbacks from each decision. Due to its self-learning characteristic and domain-independent reward function, MCTSteg has become the first reported universal non-additive steganographic framework which can work in both spatial and JPEG domains. Extensive experimental results show that MCTSteg can effectively withstand the detection of both hand-crafted feature-based and deep-learning-based steganalyzers. In both spatial and JPEG domains, the security performance of MCTSteg steadily outperforms the state of the art by a clear margin under different scenarios.

中文翻译：

---

MCTSteg：基于蒙特卡罗树搜索的通用非加性隐写术的强化学习框架


最近的研究表明，非相加图像隐写框架通过调整失真分布有效提高安全性能。然而，据我们所知，所有现有的非可加性提案都是基于手工制定的策略，并且只能应用于特定的图像领域，这严重阻碍了非可加性隐写术充分发挥其潜力。在本文中，我们提出了一种称为 MCTSteg 的自动非加性隐写失真学习框架，以消除上述限制。在强化学习范式的指导下，我们结合蒙特卡罗树搜索（MCTS）和基于隐写分析器的环境模型来构建MCTSteg。 MCTS 做出连续决策来调整失真分布，无需人工干预。我们提出的环境模型用于获取每个决策的反馈。由于其自学习特性和与领域无关的奖励函数，MCTSteg 成为第一个报道的通用非加性隐写框架，可以在空间和 JPEG 领域工作。大量实验结果表明，MCTSteg 可以有效抵御手工制作的基于特征的隐写分析器和基于深度学习的隐写分析器的检测。在空间和 JPEG 领域，MCTSteg 的安全性能在不同场景下都明显优于现有技术。