VAE-Stega: Linguistic Steganography Based on Variational Auto-Encoder
VAE-Stega: Linguistic Steganography Based on Variational Auto-Encoder
复制标题
VAE-Stega：基于变分自动编码器的语言隐写术
DOI：
10.1109/tifs.2020.3023279
复制
发表时间：
2021-01-01
影响因子：
6.8
通讯作者：
Huang, Yong-Feng
中科院分区：
文献类型：
--
作者：
Yang, Zhong-Liang;Zhang, Si-Yu;Huang, Yong-Feng
近年来，基于文本自动生成技术的语言隐写技术得到了很大的发展，被认为是一个非常有前途但也非常具有挑战性的研究课题。以往的工作主要集中在优化语言模型和条件概率编码方法，目的是生成质量更好的隐写句子。本文首先报道了我们的一些最新实验结果，这些结果似乎表明，生成的隐写文本的质量并不能完全保证其隐写安全性，甚至存在显著的感知-不可感知和统计-不可感知冲突效应(PSIC效应)。为了进一步提高隐写文本的隐蔽性和安全性，本文提出了一种新的基于变分自动编码器(VAE)的语言隐写算法，称为VAE-Stega。我们使用VAE-Stega中的编码器来学习大量正常文本的总体统计分布特征，然后使用VAE-Stega中的解码器来生成既符合统计语言模型又符合正常语句的整体统计分布的隐写语句，从而同时保证生成的隐写文本的感知不可感知性和统计不可感知性。我们设计了几个实验来测试所提出的方法。实验结果表明，该模型能很好地提高隐写语句的隐蔽性，达到最好的隐写性能。
In recent years, linguistic steganography based on text auto-generation technology has been greatly developed, which is considered to be a very promising but also a very challenging research topic. Previous works mainly focus on optimizing the language model and conditional probability coding methods, aiming at generating steganographic sentences with better quality. In this paper, we first report some of our latest experimental findings, which seem to indicate that the quality of the generated steganographic text cannot fully guarantee its steganographic security, and even has a prominent perceptual-imperceptibility and statistical-imperceptibility conflict effect (Psic Effect). To further improve the imperceptibility and security of generated steganographic texts, in this paper, we propose a new linguistic steganography based on Variational Auto-Encoder (VAE), which can be called VAE-Stega. We use the encoder in VAE-Stega to learn the overall statistical distribution characteristics of a large number of normal texts, and then use the decoder in VAE-Stega to generate steganographic sentences which conform to both of the statistical language model as well as the overall statistical distribution of normal sentences, so as to guarantee both the perceptual-imperceptibility and statistical-imperceptibility of the generated steganographic texts at the same time. We design several experiments to test the proposed method. Experimental results show that the proposed model can greatly improve the imperceptibility of the generated steganographic sentences and thus achieves the state of the art performance.