# Generative Text Steganography with Large Language Model

arXiv: https://arxiv.org/abs/2404.10229 · HTML: https://mlsanity.com/paper/2404.10229/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 16 Apr 2024.

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

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography](https://mlsanity.com/paper/2305.16936/) (2023)
- [Provably Secure Generative Linguistic Steganography](https://mlsanity.com/paper/2106.02011/) (2021)
- [Towards Near-imperceptible Steganographic Text](https://mlsanity.com/paper/1907.06679/) (2019)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)

## Built on by (most cited first, 17 of 17)

- [Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs](https://mlsanity.com/paper/2410.03768/) (2024)
- [All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting](https://mlsanity.com/paper/2503.07191/) (2025)
- [SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI](https://mlsanity.com/paper/2411.11478/) (2024)
- [All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language](https://mlsanity.com/paper/2510.09714/) (2025)
- [ImF: Implicit Fingerprint for Large Language Models](https://mlsanity.com/paper/2503.21805/) (2025)
- [Toward a Safe Internet of Agents](https://mlsanity.com/paper/2512.00520/) (2025)
- [Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems](https://mlsanity.com/paper/2601.00360/) (2026)
- [Large Language Models as Carriers of Hidden Messages](https://mlsanity.com/paper/2406.02481/) (2024)
- [LLMs can hide text in other text of the same length](https://mlsanity.com/paper/2510.20075/) (2025)
- [Moral Mazes in the Era of LLMs](https://mlsanity.com/paper/2603.20231/) (2026)
- [A Character-based Diffusion Embedding Algorithm for Enhancing the Generation Quality of Generative Linguistic Steganographic Texts](https://mlsanity.com/paper/2505.00977/) (2025)
- [DTAMS: High-Capacity Generative Steganography via Dynamic Multi-Timestep Selection and Adaptive Deviation Mapping in Latent Diffusion](https://mlsanity.com/paper/2602.01160/) (2026)
- [Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext](https://mlsanity.com/paper/2604.05273/) (2026)
- [ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry](https://mlsanity.com/paper/2604.08276/) (2026)
- [FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis](https://mlsanity.com/paper/2606.07655/) (2026)
- [What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks](https://mlsanity.com/paper/2606.09700/) (2026)
- [Synchronized Logit Steering: Real-world Steganography](https://mlsanity.com/paper/2608.14697/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have blurred the boundary of high-quality text generation between humans and machines, which is favorable for generative text steganography. While, current advanced steganographic mapping is not suitable for LLMs since most users are restricted to accessing only the black-box API or user interface of the LLMs, thereby lacking access to the training vocabulary and its sampling probabilities. In this paper, we explore a black-box generative text steganographic method based on the user interfaces of large language models, which is called LLM-Stega. The main goal of LLM-Stega is that the secure covert communication between Alice (sender) and Bob (receiver) is conducted by using the user interfaces of LLMs. Specifically, We first construct a keyword set and design a new encrypted steganographic mapping to embed secret messages. Furthermore, to guarantee accurate extraction of secret messages and rich semantics of generated stego texts, an optimization mechanism based on reject sampling is proposed. Comprehensive experiments demonstrate that the proposed LLM-Stega outperforms current state-of-the-art methods.