ALiSa: Acrostic Linguistic Steganography Based on BERT and Gibbs Sampling

Biao, YI; Wu, Hanzhou; Feng, Guorui; Zhang, Xinpeng

doi:10.1109/lsp.2022.3152126

Cited by 20 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative methods aim to perform information hiding on the text they generate, generating text and then embedding data within it [30]. The disadvantage of this approach is that hiding information on the generated text can be statistically detectable [31].…”

Section: Introductionmentioning

confidence: 99%

A Character Based Steganography Using Masked Language Modeling

Öztürk,

Mesut,

Fıdan

2024

IEEE Access

View full text Add to dashboard Cite

In this study, a steganography method based on BERT transformer model is proposed for hiding text data in cover text. The aim is to hide information by replacing specific words within the text using BERT's masked language modeling (MLM) feature. In this study, two models, finetuned for English and Turkish, are utilized to perform steganography on texts belonging to these languages. Furthermore, the proposed method can work with any transformer model that supports masked language modeling. While traditionally the hidden information in text is often limited, the proposed method allows for a significant amount of data to be hidden in the text without distorting its meaning. In this study, the proposed method is tested by hiding stego texts of varying lengths in cover text of different lengths in two different language scenarios. The test results are analyzed in terms of perplexity, KL divergence and semantic similarity. Upon examining the results, the proposed method has achieved the best results compared to other methods found in the literature, with KL divergence of 7.93 and semantic similarity of 0.99. It can be observed that the proposed method has low detectability and demonstrates success in the data hiding process.

show abstract

Section: Introductionmentioning

confidence: 99%

A Character Based Steganography Using Masked Language Modeling

Öztürk,

Mesut,

Fıdan

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the field of linguistic steganography, information can be concealed by altering word order, using specific grammar structures, or incorporating unusual vocabulary in the text. The hidden information may include encrypted messages, secret instructions, or any other content that needs to be kept confidential [ 2 ]. The applications of linguistic steganography are diverse and have far-reaching implications in the fields of information security and network security.…”

Section: Introductionmentioning

confidence: 99%

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

Lin,

Wang

2024

PLoS ONE

View full text Add to dashboard Cite

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.

show abstract

“…The majority of early steganographic algorithms were originally developed for digital images. In recent years, thanks to deep learning, the performance of natural language processing technology has been greatly improved, which promotes utilizing text for steganography to become a hot topic [4,5,6,7,8]. Compared to image steganography, natural language steganography (or say text steganography) overcomes the problem of robustness, i.e., image steganography may be failed due to lossy compression, but texts can survive from noisy channel.…”

Section: Introductionmentioning

confidence: 99%

Prompting Steganography: A New Paradigm

2024

View full text Add to dashboard Cite

Recent studies show that scaling pre-trained language models can lead to a significantly improved model capacity on downstream tasks, resulting in a new research direction called large language models (LLMs). A remarkable application of LLMs is ChatGPT, which is a powerful large language model capable of generating human-like text based on context and past conversations. It is demonstrated that LLMs have impressive skills in reasoning, especially when using prompting strategies. In this paper, we explore the possibility of applying LLMs to the field of steganography, which is referred to as the art of hiding secret data into an innocent cover for covert communication. Our purpose is not to combine an LLM into an already designed steganographic system to boost the performance, which follows the conventional framework of steganography. Instead, we expect that, through prompting, an LLM can realize steganography by itself, which is defined as prompting steganography and may be a new paradigm of steganography. We show that, by reasoning, an LLM can embed secret data into a cover, and extract secret data from a stego, with an error rate. This error rate, however, can be reduced by optimizing the prompt, which may shed light on further research.

show abstract

ALiSa: Acrostic Linguistic Steganography Based on BERT and Gibbs Sampling

Cited by 20 publications

References 21 publications

A Character Based Steganography Using Masked Language Modeling

A Character Based Steganography Using Masked Language Modeling

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

Prompting Steganography: A New Paradigm

Contact Info

Product

Resources

About