# GTSD: Generative Text Steganography Based on Diffusion Model

arXiv: https://arxiv.org/abs/2504.19433 · HTML: https://mlsanity.com/paper/2504.19433/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 7 of 7)

- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation](https://mlsanity.com/paper/2305.09515/) (2023)
- [Self-conditioned Embedding Diffusion for Text Generation](https://mlsanity.com/paper/2211.04236/) (2022)
- [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)
- [PDF Steganography based on Chinese Remainder Theorem](https://mlsanity.com/paper/1506.01256/) (2015)

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

- [HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework](https://mlsanity.com/paper/2607.23597/) (2026)

## Abstract (arXiv)

With the rapid development of deep learning, existing generative text steganography methods based on autoregressive models have achieved success. However, these autoregressive steganography approaches have certain limitations. Firstly, existing methods require encoding candidate words according to their output probability and generating each stego word one by one, which makes the generation process time-consuming. Secondly, encoding and selecting candidate words changes the sampling probabilities, resulting in poor imperceptibility of the stego text. Thirdly, existing methods have low robustness and cannot resist replacement attacks. To address these issues, we propose a generative text steganography method based on a diffusion model (GTSD), which improves generative speed, robustness, and imperceptibility while maintaining security. To be specific, a novel steganography scheme based on diffusion model is proposed to embed secret information through prompt mapping and batch mapping. The prompt mapping maps secret information into a conditional prompt to guide the pre-trained diffusion model generating batches of candidate sentences. The batch mapping selects stego text based on secret information from batches of candidate sentences. Extensive experiments show that the GTSD outperforms the SOTA method in terms of generative speed, robustness, and imperceptibility while maintaining comparable anti-steganalysis performance. Moreover, we verify that the GTSD has strong potential: embedding capacity is positively correlated with prompt capacity and model batch sizes while maintaining security.