# Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding

arXiv: https://arxiv.org/abs/2010.00677 · HTML: https://mlsanity.com/paper/2010.00677/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

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

- [Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model](https://mlsanity.com/paper/2104.09833/) (2021)
- [Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation](https://mlsanity.com/paper/2305.05010/) (2023)
- [TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent](https://mlsanity.com/paper/2505.20118/) (2025)
- [Addressing Segmentation Ambiguity in Neural Linguistic Steganography](https://mlsanity.com/paper/2211.06662/) (2022)
- [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)
- [Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models](https://mlsanity.com/paper/2508.20718/) (2025)
- [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)
- [Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography](https://mlsanity.com/paper/2604.09066/) (2026)
- [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)
- [Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems](https://mlsanity.com/paper/2609.39050/) (2026)
- [An LLM Framework For Cryptography Over Chat Channels](https://mlsanity.com/paper/2504.08871/) (2025)
- [A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges](https://mlsanity.com/paper/2608.29077/) (2026)
- [CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding](https://mlsanity.com/paper/2609.10744/) (2026)
- [Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key](https://mlsanity.com/paper/2610.18359/) (2026)

## Abstract (arXiv)

Linguistic steganography studies how to hide secret messages in natural language cover texts. Traditional methods aim to transform a secret message into an innocent text via lexical substitution or syntactical modification. Recently, advances in neural language models (LMs) enable us to directly generate cover text conditioned on the secret message. In this study, we present a new linguistic steganography method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model. We formally analyze the statistical imperceptibility of this method and empirically show it outperforms the previous state-of-the-art methods on four datasets by 15.3% and 38.9% in terms of bits/word and KL metrics, respectively. Finally, human evaluations show that 51% of generated cover texts can indeed fool eavesdroppers.