Linguistic Steganography Research Articles

New Uses for Linguistic Steganography

The development of modern linguistic steganography and steganalysis technologies creates new opportunities for use cases to be discovered. Our previous research points to high viability of methods such as trigger-container implementation for the traditional goal of covert information relay. While the findings were significant, it appears that linguistic steganography may have additional applications unrelated to this traditional use case. We aim to analyze how these technologies may be beneficially used in VR-environments, digital governance and for recreational purposes and how these advancements give rise to new speech practices. By investigating the broader implications of linguistic steganography, we hope to uncover innovative ways in which this technology can be harnessed to improve information security, facilitate immersive experiences, and contribute to the development of more sophisticated language-based communication strategies. Using linguistic steganography in VR can improve user experience, ensure sensitive information relay, create new game scenarios. In digital governance these technologies can be used to protect data, ensure secure communications and develop new methods of content analysis. In entertainment, linguistic steganography can be a useful tool for creating riddles, ciphers, and alternative modes of communication in games and other entertainment products. All this gives a new impetus to the development of language practices and prospects for further research in this area.

Enhancing Contextual Masking in Reversible Linguistic Steganography with Ensemble Methods

Various cybercrimes can be prevented by text authentication that is responsible for preserving digital identities and contents. Digital signatures come in handy as a way of authenticating texts, which is an extensively used method. One approach to this problem is linguistic steganography, which allows hiding the signature in other words within the text and thereby facilitating efficient data management. However, it should be noted that there is a danger that these kinds of changes may result in inappropriate decisions being taken by automated computing systems not to mention change their final outputs (unseen). As such, many people are becoming more concerned with the possibility of reversing steganography so that it becomes possible to eliminate any distortions made during the process. This paper uses Contextual masking instead of masking randomly with BERT model. The goal behind this research was developing a natural language text specific Reversible Steganographic System. Our model uses pre-trained BERT as a transformer based masked language model and reversibly embeds messages through predictive word substitution. To quantify predictive uncertainty, we introduce an adaptive steganographic technique using Bayesian deep learning. This experiment shows us how our proposed system balances imperceptibility with capacity while maintaining near semantics at all times. Also, we integrate ensemble methods instead of Monte Carlo to balance the imperceptibility.

Joint Linguistic Steganography With BERT Masked Language Model and Graph Attention Network

Joint Linguistic Steganography With BERT Masked Language Model and Graph Attention Network

A novel method for linguistic steganography by English translation using attention mechanism and probability distribution theory.

To enhance our ability to model long-range semantical dependencies, we introduce a novel approach for linguistic steganography through English translation. This method leverages attention mechanisms and probability distribution theory, known as NMT-stega (Neural Machine Translation-steganography). Specifically, to optimize translation accuracy and make full use of valuable source text information, we employ an attention-based NMT model as our translation technique. To address potential issues related to the degradation of text quality due to secret information embedding, we have devised a dynamic word pick policy based on probability variance. This policy adaptively constructs an alternative set and dynamically adjusts embedding capacity at each time step, guided by variance thresholds. Additionally, we have incorporated prior knowledge into the model by introducing a hyper-parameter that balances the contributions of the source and target text when predicting the embedded words. Extensive ablation experiments and comparative analyses, conducted on a large-scale Chinese-English corpus, validate the effectiveness of the proposed method across several critical aspects, including embedding rate, text quality, anti-steganography, and semantical distance. Notably, our numerical results demonstrate that the NMT-stega method outperforms alternative approaches in anti-steganography tasks, achieving the highest scores in two steganalysis models, NFZ-WDA (with score of 53) and LS-CNN (with score of 56.4). This underscores the superiority of NMT-stega in the anti-steganography attack task. Furthermore, even when generating longer sentences, with average lengths reaching 47 words, our method maintains strong semantical relationships, as evidenced by a semantic distance of 87.916. Moreover, we evaluate the proposed method using two metrics, Bilingual Evaluation Understudy and Perplexity, and achieve impressive scores of 42.103 and 23.592, respectively, highlighting its exceptional performance in the machine translation task.

Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding

Linguistic steganography (LS) aims to embed secret information into a highly encoded text for covert communication. It can be roughly divided to two main categories, i.e., modification based LS (MLS) and generation based LS (GLS). MLS embeds secret data by slightly modifying a given text without impairing the meaning of the text, whereas GLS uses a well trained language model to directly generate a text carrying secret data. A common disadvantage for MLS methods is that the embedding payload is very small, whose return is well preserving the semantic quality of the text. In contrast, GLS enables the data hider to embed a large payload, which has to pay the high price of uncontrollable semantics. In this paper, we propose a novel LS method to modify a given text by pivoting it between two different languages and embed secret data using a semantic-aware information encoding strategy. Our purpose is to alter the expression of the given text, enabling a large payload to be embedded while keeping the semantic information unchanged. Experiments have shown that the proposed work not only achieves a large embedding payload, but also shows superior performance in maintaining the semantic consistency and resisting linguistic steganalysis.

Context-Aware Linguistic Steganography Model Based on Neural Machine Translation

Context-Aware Linguistic Steganography Model Based on Neural Machine Translation

Reversible Linguistic Steganography With Bayesian Masked Language Modeling

Text authentication serves a vital role in the defense of digital identity and content against various types of cybercrime. The use of a digital signature is a common cryptographic technique for text authentication. Linguistic steganography can be applied to further conceal a digital signature within the corresponding text to facilitate data management. However, steganographic distortion lurking in the text, albeit almost imperceptible, has the potential to cause automatic computing machinery to make biased decisions. This has led to an interest in the pursuit of reversibility, the ability to reverse a steganographic process and remove distortion. In this article, we propose a reversible steganographic system for natural language text. We use a pre-trained transformer neural network for masked language modeling and embed messages in a reversible manner via predictive word substitution. Furthermore, we derive an adaptive steganographic route by taking account of predictive uncertainty, which is quantified based on a theoretical framework of Bayesian deep learning. Experimental results show that the proposed steganographic system can attain a proper balance between capacity, imperceptibility, and reversibility with close semantic and sentimental similarities between cover and stego texts.

Detection of Generative Linguistic Steganography Based on Explicit and Latent Text Word Relation Mining Using Deep Learning

Covert communication channels can be easily constructed using text steganography based on social media. Offenders can easily utilize these channels to engage in various criminal activities, which brings great challenges in maintaining the security of cyberspace. Among the text information hiding methods, generative linguistic steganography poses the biggest threat to network security because it does not need the original carrier and has high embedding efficiency. The existing generative linguistic steganalysis methods fail to deeply mine text word relation, hence the detection performance is relatively unsatisfactory. In this paper, we prove that there is explicit and latent steganography-sensitive text word relation. Based on this, we propose a generative linguistic steganalysis method based on Explicit and Latent text word relation Mining, named ELM. Firstly, we employ a distributed readin module to convert words into real number vectors. Then, MRA (Mining Relation by Attentions) is proposed to mine the explicit and latent text word relation. Finally, global adaptive classification module is presented to exploit the mined relation feature to predict whether secret information is embedded in the current text segment. Experimental results demonstrate that the detection performance of ELM is better than the existing generative linguistic steganalysis methods.

Linguistic Steganalysis Toward Social Network

With the rapid development of the internet and social media, linguistic steganography can be easily abused in social networks to make considerable damage to varied aspects like personal privacy, network virus and national defense. Currently, considerable linguistic steganalysis methods are proposed to detect harmful steganographic carriers. However, almost all the existing methods fail in real social networks, since they are only devoted to the linguistic features that are extreme insufficient owing to the extreme sparsity and extreme fragmentation challenges of real social networks. In this paper, we attempt to fill the long-standing gap that the datasets and effective methods are absent for hunting steganographic texts in social network scenarios. Concretely, we construct a dataset called Stego-Sandbox to simulate the real social network scenarios, which contains texts and their relation. And we propose an effective linguistic steganalysis framework integrating linguistic features contained in texts and context features represented by these connections. Extensive experimental results demonstrate owing to the captured context features, our proposed framework can effectively compensate for shortcomings of these existing methods and tremendously improve their detection ability in real social network scenarios.

Topic Controlled Steganography via Graph-to-Text Generation

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.

PNG-Stega: Progressive Non-Autoregressive Generative Linguistic Steganography

The autoregressive-based model with the left-to-right generation order has been a predominant paradigm for generative linguistic steganography. However, such steganography does not perform well on semantic control and content planning, which is forced by the secret message during the generation process. To mitigate this issue and efficiently produce high-quality steganographic texts (stegotexts), we present a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</i> rogressive <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> on-autoregressive <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</i> enerative linguistic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Stega</i> nography (PNG-Stega), which encodes secret messages and extends the context to generate stegotexts in a multi-round insertion manner. Each round continuously refines the generated steganographic sequences on the premise of the global information of the previous round, while striving to decline the adverse effects of steganographic encoding on text quality. Moreover, for enhancing the semantic internal dependency of stegotexts, we utilize a constraint word sequences extraction scheme to obtain keywords to initialize the skeleton of targeted stegotexts, then expand the existing keywords with insertion operations. Experimental results demonstrate that PNG-Stega outperforms compared methods in terms of imperceptibility and anti-steganalysis ability. In particular, PNG-Stega provides high information hiding efficiency, even exceeding the autoregressive methods by around 2 times.

Steganography using Syntactic Method

Information security, which is becoming more crucial as information sharing plays an increasingly significant part in the day-to-day activities of today's people, is one of the methods that may be used for information security. For the sake of information security, we present a method to linguistic steganography that is based on syntactic banks.

A Secure and Disambiguating Approach for Generative Linguistic Steganography

A Secure and Disambiguating Approach for Generative Linguistic Steganography

Linguistic Steganography Based on Adaptive Probability Distribution

Text has become one of the most extensively used digital media in Internet, which provides steganography an effective carrier to realize confidential message hiding. Nowadays, generation-based linguistic steganography has made a significant breakthrough due to the progress of deep learning. However, previous methods based on recurrent neural network have two deviations including exposure bias and embedding deviation, which seriously destroys the security of steganography. In this article, we propose a novel linguistic steganographic model based on adaptive probability distribution and generative adversarial network, which achieves the goal of hiding secret messages in the generated text while guaranteeing high security performance. First, the steganographic generator is trained by using generative adversarial network to effectively tackle the exposure bias, and then the candidate pool is obtained by a probability similarity function at each time step, which alleviates the embedding deviation through dynamically maintaining the diversity of probability distribution. Third, to further improve the security, a novel strategy that conducts information embedding during model training is put forward. We design various experiments from different aspects to verify the performance of the proposed model, including imperceptibility, statistical distribution, anti-steganalysis ability. demonstrate that our proposed model outperforms the current state-of-the-art steganographic schemes.

LZW-CIE: a high-capacity linguistic steganography based on LZW char index encoding

LZW-CIE: a high-capacity linguistic steganography based on LZW char index encoding

Сurrent state and prospects of steganography development in telecommunication systems

At present, it is necessary to ensure stable, continuous and hidden transmission of information, so it is advisable to consider the hiding of the very fact of the transmission of the message. Thus, the risk of access to information with limited access is significantly reduced. Along with this, additional messages can be encrypted. Thus, steganography is a science that provides information exchange in such a way that the very fact of the existence of a confidential message is hidden. It complements cryptography (data encryption) with another level of security rather than replacing it. To date, the use of steganography involves a number of methods for protecting information resources. It is divided into linguistic and technical. In turn, linguistic steganography is divided into: semagrams, open codes and closed ciphers. Technical steganography is divided into stego-text, stego-audio, stego-video and stego-image. For this purpose, such message carriers as images, text, audio or video are used. The media message and message (information) that needs to be hidden is broken down into bits, and these bits of information are hidden in each bit (in bits) of the media message. The information is encrypted by changing the different properties of the message carrier. Technical steganography uses special methods of signal protection, which it is advisable to implement in promising departmental means of digital communication. One of the ways to increase the hidden fact of the transmission of digital message by steganographic methods is the use of streamlined electromagnetic steganography. This concept involves the transmission of a low-power digital signal simultaneously with the radiation of a significantly more powerful legitimate source. Such a source, for example, can be a digital broadcasting transmitter. The hiding message transmission algorithm consists of three main stages: 1) the formation of electromagnetic radiation containing a hidden message 2) the additive linear addition of electromagnetic radiation containing a hidden message and stream electromagnetic container in space, 3) the demodulation of the total signal, followed by the release of the hidden message. Electromagnetic steganography, as an independent branch in the general theory of stego, with the creation of the theory of multiplayer detection has the prospects of qualitatively new development. The approaches of this theory allow to mask the hidden message not by reducing the spectral power density due to the use of broadband signals, but by ensuring the possibility of concealment of the ocular spectrum of the hidden message emitter under the ambient energy spectrum of radiation.

Generation-based linguistic steganography with controllable security

Generation-based linguistic steganography with controllable security

Autoregressive Linguistic Steganography Based on BERT and Consistency Coding

Linguistic steganography (LS) conceals the presence of communication by embedding secret information into a text. How to generate a high-quality text carrying secret information is a key problem. With the widespread application of deep learning in natural language processing, recent algorithms use a language model (LM) to generate the steganographic text, which provides a higher payload compared with many previous arts. However, the security still needs to be enhanced. To tackle this problem, we propose a novel autoregressive LS algorithm based on BERT and consistency coding, which achieves a better trade-off between embedding payload and system security. In the proposed work, based on the introduction of the masked LM, given a text, we use consistency coding to make up for the shortcomings of block coding used in the previous work so that we can encode arbitrary-size candidate token set and take advantage of the probability distribution for information hiding. The masked positions to be embedded are filled with tokens determined by an autoregressive manner to enhance the connection between contexts and therefore maintain the quality of the text. Experimental results have shown that compared with related works, the proposed work improves the fluency of the steganographic text while guaranteeing security and also increases the embedding payload to a certain extent.

MTS-Stega: Linguistic Steganography Based on Multi-Time-Step.

Generative linguistic steganography encodes candidate words with conditional probability when generating text by language model, and then, it selects the corresponding candidate words to output according to the confidential message to be embedded, thereby generating steganographic text. The encoding techniques currently used in generative text steganography fall into two categories: fixed-length coding and variable-length coding. Because of the simplicity of coding and decoding and the small computational overhead, fixed-length coding is more suitable for resource-constrained environments. However, the conventional text steganography mode selects and outputs a word at one time step, which is highly susceptible to the influence of confidential information and thus may select words that do not match the statistical distribution of the training text, reducing the quality and concealment of the generated text. In this paper, we inherit the decoding advantages of fixed-length coding, focus on solving the problems of existing steganography methods, and propose a multi-time-step-based steganography method, which integrates multiple time steps to select words that can carry secret information and fit the statistical distribution, thus effectively improving the text quality. In the experimental part, we choose the GPT-2 language model to generate the text, and both theoretical analysis and experiments prove the effectiveness of the proposed scheme.

SeSy: Linguistic Steganalysis Framework Integrating Semantic and Syntactic Features

With the rapid development of natural language processing technology and linguistic steganography, linguistic steganalysis gains considerable interest in recent years. Current advanced methods dominantly focus on statistical features in semantic view yet ignore syntax structure of text, which leads to limited performance to some newly statistically indistinguishable steganography algorithms. To fill this gap, in this paper, we propose a novel linguistic steganalysis framework named SeSy to integrate both <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">se</b> mantic and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sy</b> ntactic features. Specifically, we propose to employ transformer-architecture language model as semantics extractor and leverage a graph attention network to retain syntactic features. Extensive experimental results show that owing to additional syntactic information, the SeSy framework effectively brings about remarkable improvement to current advanced linguistic steganalysis methods.