Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
复制标题
使用生成对抗网络的自动隐写失真学习
DOI：
10.1109/lsp.2017.2745572
复制
发表时间：
2017-10-01
影响因子：
3.9
通讯作者：
Huang, Jiwu
中科院分区：
文献类型：
--
作者：
Tang, Weixuan;Tan, Shunquan;Huang, Jiwu
生成式对抗网络具有两个相互竞争的子网络的统一框架，可以有效地生成与真实的对应物难以区分的人工样本。在这封信中，我们首先提出了一个自动隐写失真学习框架，使用生成对抗网络，它是由一个隐写生成子网络和隐写分析判别子网络。通过交替训练这两个对立的子网络，我们提出的框架可以自动学习嵌入变化概率为每个像素在一个给定的空间覆盖图像。然后，学习的嵌入变化概率可以转换为嵌入失真，这可以在现有的最小失真嵌入框架中采用。在此框架下，失真函数直接关系到对抗进化隐写分析器的不可检测性。实验结果表明，通过对抗性学习，我们提出的框架可以有效地从一开始的几乎幼稚的随机$\pm 1$嵌入发展到更高级的内容自适应嵌入，它试图在纹理区域中嵌入秘密比特。随着训练迭代次数的增加，安全性能也在稳步提高。
Generative adversarial network has shown to effectively generate artificial samples indiscernible from their real counterparts with a united framework of two subnetworks competing against each other. In this letter, we first propose an automatic steganographic distortion learning framework using a generative adversarial network, which is composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. Via alternately training these two oppositional subnetworks, our proposed framework can automatically learn embedding change probabilities for every pixel in a given spatial cover image. The learnt embedding change probabilities can then be converted to embedding distortions, which can be adopted in the existing framework of minimal-distortion embedding. Under this framework, the distortion function is directly related to the undetectability against the oppositional evolving steganalyzer. Experimental results show that with adversarial learning, our proposed framework can effectively evolve from nearly naïve random $\pm 1$ embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions. The security performance is also steadily improved with increasing training iterations.