# A Content-Preserving Secure Linguistic Steganography

arXiv: https://arxiv.org/abs/2511.12565 · HTML: https://mlsanity.com/paper/2511.12565/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [Generating Steganographic Text with LSTMs](https://mlsanity.com/paper/1705.10742/) (2017)
- [Provably Secure Generative Linguistic Steganography](https://mlsanity.com/paper/2106.02011/) (2021)
- [Towards Near-imperceptible Steganographic Text](https://mlsanity.com/paper/1907.06679/) (2019)
- [Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding](https://mlsanity.com/paper/2010.00677/) (2020)
- [Learning Better Masking for Better Language Model Pre-training](https://mlsanity.com/paper/2208.10806/) (2022)
- [Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding](https://mlsanity.com/paper/2203.03795/) (2022)
- [Autoregressive Linguistic Steganography Based on BERT and Consistency Coding](https://mlsanity.com/paper/2203.13972/) (2022)
- [From Covert Hiding to Visual Editing: Robust Generative Video Steganography](https://mlsanity.com/paper/2401.00652/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges](https://mlsanity.com/paper/2608.29077/) (2026)

## Abstract (arXiv)

Existing linguistic steganography methods primarily rely on content transformations to conceal secret messages. However, they often cause subtle yet looking-innocent deviations between normal and stego texts, posing potential security risks in real-world applications. To address this challenge, we propose a content-preserving linguistic steganography paradigm for perfectly secure covert communication without modifying the cover text. Based on this paradigm, we introduce CLstega (textitContent-preserving textitLinguistic textitsteganography), a novel method that embeds secret messages through controllable distribution transformation. CLstega first applies an augmented masking strategy to locate and mask embedding positions, where MLM(masked language model)-predicted probability distributions are easily adjustable for transformation. Subsequently, a dynamic distribution steganographic coding strategy is designed to encode secret messages by deriving target distributions from the original probability distributions. To achieve this transformation, CLstega elaborately selects target words for embedding positions as labels to construct a masked sentence dataset, which is used to fine-tune the original MLM, producing a target MLM capable of directly extracting secret messages from the cover text. This approach ensures perfect security of secret messages while fully preserving the integrity of the original cover text. Experimental results show that CLstega can achieve a 100% extraction success rate, and outperforms existing methods in security, effectively balancing embedding capacity and security.