Neural Linguistic Steganography

Ziegler, Zachary M.; Deng, Yuntian; Rush, Alexander M.

doi:10.48550/arxiv.1909.01496

Cited by 6 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On each symbol recursion, an interval [l i , u i ) (which is initially set to [0, 1)) is successively partioned according to the cumulative distribution of the symbol, and narrowed down by taking the sub-interval containing the symbol value as the new interval [l i+1 , u i+1 ). Following Zigler et al [43], we adopted a fixed-precision implementation of arithmetic coding [44].…”

Section: B Stegosampling Based On Arithmetic Codingmentioning

confidence: 99%

“…If the impact of truncation, quantization and blocking of secret message is ignored (prc tends to infinity and the secret message m has infinite length), q(x i |x <i ) is actually identical to p(x i |x <i ) and it is able to achieve the optimal imperceptibility. Arithmetic coding is widely applied in generative linguistic and audio steganography due to its advantage in embedding capacity and imperceptibility [34], [43], [46]. But as far as we know, there hasn't been any research about generative image steganography with arithmetic-coding-based stegosampling.…”

Section: Imperceptibilitymentioning

confidence: 99%

See 1 more Smart Citation

Pixel-Stega: Generative Image Steganography Based on Autoregressive Models

Zhang¹,

Yang²,

Tu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this letter, we explored generative image steganography based on autoregressive models. We proposed Pixel-Stega, which implements pixel-level information hiding with autoregressive models and arithmetic coding algorithm. Firstly, one of the autoregressive models, PixelCNN++, is utilized to produce explicit conditional probability distribution of each pixel. Secondly, secret messages are encoded to the selection of pixels through steganographic sampling (stegosampling) based on arithmetic coding. We carried out qualitative and quantitative assessment on gray-scale and colour image datasets. Experimental results show that Pixel-Stega is able to embed secret messages adaptively according to the entropy of the pixels to achieve both high embedding capacity (up to 4.3 bpp) and nearly perfect imperceptibility (about 50% detection accuracy). 1

show abstract

Section: B Stegosampling Based On Arithmetic Codingmentioning

confidence: 99%

Section: Imperceptibilitymentioning

confidence: 99%

Pixel-Stega: Generative Image Steganography Based on Autoregressive Models

Zhang¹,

Yang²,

Tu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, text is one of the most commonly used communication carriers in people's daily life [11]. Therefore, studying how to effectively embed hidden information in texts has attracted a lot of researchers' interest [9], [12]- [20]. Some early text steganography techniques were mainly implemented by making minor modifications to the text, such as adjusting word spacing [21], or by synonymizing specific words and phrases [22].…”

mentioning

confidence: 99%

“…These technologies are good attempts, but usually they can only have a very low embedding rate, so it is difficult for them to be practical [9]. Therefore, later researchers began to try to use the text automatic generation model to achieve information embedding [9], [16]- [20].…”

mentioning

confidence: 99%

“…Since the carrier will not be given in advance, the first challenge is: How to generate a semantically complete and natural enough steganographic sample? In order to solve this challenge, previous researchers have done a lot of works [9], [16]- [20]. From the first generation of steganography based on specific syntax structure [13], to the later generation of steganography based on Markov model [14], [23], [24], and the recent emergence of a method of steganography based on neural network [9], [17]- [20], researchers have gradually been able to generate high-quality steganographic sentences.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph

Yang,

Gong,

et al. 2020

Preprint

View full text Add to dashboard Cite

Most of the existing text generative steganographic methods are based on coding the conditional probability distribution of each word during the generation process, and then selecting specific words according to the secret information, so as to achieve information hiding. Such methods have their limitations which may bring potential security risks. Firstly, with the increase of embedding rate, these models will choose words with lower conditional probability, which will reduce the quality of the generated steganographic texts; secondly, they can not control the semantic expression of the final generated steganographic text. This paper proposes a new text generative steganography method which is quietly different from the existing models. We use a Knowledge Graph (KG) to guide the generation of steganographic sentences. On the one hand, we hide the secret information by coding the path in the knowledge graph, but not the conditional probability of each generated word; on the other hand, we can control the semantic expression of the generated steganographic text to a certain extent. The experimental results show that the proposed model can guarantee both the quality of the generated text and its semantic expression, which is a supplement and improvement to the current text generation steganography.

show abstract

Topic Controlled Steganography via Graph-to-Text Generation

Sun¹,

Li²,

Zhang³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Generation-based linguistic steganography is a popular research area of information hiding. The text generative steganographic method based on conditional probability coding is the direction that researchers have recently paid attention to. However, in the course of our experiment, we found that the secret information hiding in the text tends to destroy the statistical distribution characteristics of the original text, which indicates that this method has the problem of the obvious reduction of text quality when the embedding rate increases, and that the topic of generated texts is uncontrollable, so there is still room for improvement in concealment. In this paper, we propose a topic-controlled steganography method which is guided by graph-to-text generation. The proposed model can automatically generate steganographic texts carrying secret messages from knowledge graphs, and the topic of the generated texts is controllable. We also provide a graph path coding method with corresponding detailed algorithms for graph-to-text generation. Different from traditional linguistic steganography methods, we encode the secret information during graph path coding rather than using conditional probability. We test our method in different aspects and compare it with other text generative steganographic methods. The experimental results show that the model proposed in this paper can effectively improve the quality of the generated text and significantly improve the concealment of steganographic text.

show abstract

Neural Linguistic Steganography

Cited by 6 publications

References 0 publications

Pixel-Stega: Generative Image Steganography Based on Autoregressive Models

Pixel-Stega: Generative Image Steganography Based on Autoregressive Models

Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph

Topic Controlled Steganography via Graph-to-Text Generation

Contact Info

Product

Resources

About