# General Framework for Reversible Data Hiding in Texts Based on Masked Language Modeling

arXiv: https://arxiv.org/abs/2206.10112 · HTML: https://mlsanity.com/paper/2206.10112/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 21 Jun 2022.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Generating Steganographic Text with LSTMs](https://mlsanity.com/paper/1705.10742/) (2017)
- [Provably Secure Generative Linguistic Steganography](https://mlsanity.com/paper/2106.02011/) (2021)
- [TS-RNN: Text Steganalysis Based on Recurrent Neural Networks](https://mlsanity.com/paper/1905.13087/) (2019)
- [Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding](https://mlsanity.com/paper/2203.03795/) (2022)
- [Exploiting Language Model for Efficient Linguistic Steganalysis](https://mlsanity.com/paper/2107.12168/) (2021)
- [Autoregressive Linguistic Steganography Based on BERT and Consistency Coding](https://mlsanity.com/paper/2203.13972/) (2022)
- [Prediction-error of Prediction Error (PPE)-based Reversible Data Hiding](https://mlsanity.com/paper/1604.04984/) (2016)
- [Reversible Video Data Hiding Using Zero QDCT Coefficient-Pairs](https://mlsanity.com/paper/1804.06628/) (2018)

## 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)

With the fast development of natural language processing, recent advances in information hiding focus on covertly embedding secret information into texts. These algorithms either modify a given cover text or directly generate a text containing secret information, which, however, are not reversible, meaning that the original text not carrying secret information cannot be perfectly recovered unless much side information are shared in advance. To tackle with this problem, in this paper, we propose a general framework to embed secret information into a given cover text, for which the embedded information and the original cover text can be perfectly retrieved from the marked text. The main idea of the proposed method is to use a masked language model to generate such a marked text that the cover text can be reconstructed by collecting the words of some positions and the words of the other positions can be processed to extract the secret information. Our results show that the original cover text and the secret information can be successfully embedded and extracted. Meanwhile, the marked text carrying secret information has good fluency and semantic quality, indicating that the proposed method has satisfactory security, which has been verified by experimental results. Furthermore, there is no need for the data hider and data receiver to share the language model, which significantly reduces the side information and thus has good potential in applications.