# Provably Secure Generative Linguistic Steganography

arXiv: https://arxiv.org/abs/2106.02011 · HTML: https://mlsanity.com/paper/2106.02011/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [Generating Steganographic Text with LSTMs](https://mlsanity.com/paper/1705.10742/) (2017)
- [Towards Near-imperceptible Steganographic Text](https://mlsanity.com/paper/1907.06679/) (2019)
- [Automatically Generate Steganographic Text Based on Markov Model and Huffman Coding](https://mlsanity.com/paper/1811.04720/) (2018)
- [An Approach for Text Steganography Based on Markov Chains](https://mlsanity.com/paper/1409.0915/) (2014)

## Built on by (most cited first, 30 of 34)

- [Perfectly Secure Steganography Using Minimum Entropy Coupling](https://mlsanity.com/paper/2210.14889/) (2022)
- [Generative Text Steganography with Large Language Model](https://mlsanity.com/paper/2404.10229/) (2024)
- [The Steganographic Potentials of Language Models](https://mlsanity.com/paper/2505.03439/) (2025)
- [Are Robust LLM Fingerprints Adversarially Robust?](https://mlsanity.com/paper/2509.26598/) (2025)
- [Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding](https://mlsanity.com/paper/2203.03795/) (2022)
- [Addressing Segmentation Ambiguity in Neural Linguistic Steganography](https://mlsanity.com/paper/2211.06662/) (2022)
- [ImF: Implicit Fingerprint for Large Language Models](https://mlsanity.com/paper/2503.21805/) (2025)
- [Provably Secure Disambiguating Neural Linguistic Steganography](https://mlsanity.com/paper/2403.17524/) (2024)
- [OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions](https://mlsanity.com/paper/2410.04328/) (2024)
- [Zero-shot Generative Linguistic Steganography](https://mlsanity.com/paper/2403.10856/) (2024)
- [UP4LS: User Profile Constructed by Multiple Attributes for Enhancing Linguistic Steganalysis](https://mlsanity.com/paper/2311.01775/) (2023)
- [Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel](https://mlsanity.com/paper/2401.15656/) (2024)
- [Efficient Provably Secure Linguistic Steganography via Range Coding](https://mlsanity.com/paper/2604.08052/) (2026)
- [Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments](https://mlsanity.com/paper/2110.07009/) (2021)
- [Provable Secure Steganography Based on Adaptive Dynamic Sampling](https://mlsanity.com/paper/2504.12579/) (2025)
- [Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography](https://mlsanity.com/paper/2510.06565/) (2025)
- [Invisible Safety Threat: Malicious Finetuning for LLM via Steganography](https://mlsanity.com/paper/2603.08104/) (2026)
- [Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography](https://mlsanity.com/paper/2604.09066/) (2026)
- [General Framework for Reversible Data Hiding in Texts Based on Masked Language Modeling](https://mlsanity.com/paper/2206.10112/) (2022)
- [GTSD: Generative Text Steganography Based on Diffusion Model](https://mlsanity.com/paper/2504.19433/) (2025)
- [GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis](https://mlsanity.com/paper/2505.17085/) (2025)
- [A High-Capacity and Secure Disambiguation Algorithm for Neural Linguistic Steganography](https://mlsanity.com/paper/2510.02332/) (2025)
- [A high-capacity linguistic steganography based on entropy-driven rank-token mapping](https://mlsanity.com/paper/2510.23035/) (2025)
- [A Content-Preserving Secure Linguistic Steganography](https://mlsanity.com/paper/2511.12565/) (2025)
- [Steganography Without Modification: Hidden Communication via LLM Seeds](https://mlsanity.com/paper/2606.09135/) (2026)
- [HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework](https://mlsanity.com/paper/2607.23597/) (2026)
- [Pixel-Stega: Generative Image Steganography Based on Autoregressive Models](https://mlsanity.com/paper/2112.10945/) (2021)
- [On Information Hiding in Natural Language Systems](https://mlsanity.com/paper/2203.06512/) (2022)
- [Verifier-Bound Communication for LLM Agents: Certified Bounds on Covert Signaling](https://mlsanity.com/paper/2603.00381/) (2026)
- [Text Steganography with Dynamic Codebook and Multimodal Large Language Model](https://mlsanity.com/paper/2604.20269/) (2026)

## Abstract (arXiv)

Generative linguistic steganography mainly utilized language models and applied steganographic sampling (stegosampling) to generate high-security steganographic text (stegotext). However, previous methods generally lead to statistical differences between the conditional probability distributions of stegotext and natural text, which brings about security risks. In this paper, to further ensure security, we present a novel provably secure generative linguistic steganographic method ADG, which recursively embeds secret information by Adaptive Dynamic Grouping of tokens according to their probability given by an off-the-shelf language model. We not only prove the security of ADG mathematically, but also conduct extensive experiments on three public corpora to further verify its imperceptibility. The experimental results reveal that the proposed method is able to generate stegotext with nearly perfect security.