# Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments

arXiv: https://arxiv.org/abs/2110.07009 · HTML: https://mlsanity.com/paper/2110.07009/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 44 references that are in the map.
- First posted on arXiv 13 Oct 2021.

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

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [Provably Secure Generative Linguistic Steganography](https://mlsanity.com/paper/2106.02011/) (2021)
- [Towards Near-imperceptible Steganographic Text](https://mlsanity.com/paper/1907.06679/) (2019)
- [TS-RNN: Text Steganalysis Based on Recurrent Neural Networks](https://mlsanity.com/paper/1905.13087/) (2019)
- [Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding](https://mlsanity.com/paper/2010.00677/) (2020)
- [Lost in the Digital Wild: Hiding Information in Digital Activities](https://mlsanity.com/paper/1809.02888/) (2018)

## Built on by (most cited first, 2 of 2)

- [TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent](https://mlsanity.com/paper/2505.20118/) (2025)
- [A high-capacity linguistic steganography based on entropy-driven rank-token mapping](https://mlsanity.com/paper/2510.23035/) (2025)

## Abstract (arXiv)

State of the art generative models of human-produced content are the focus of many recent papers that explore their use for steganographic communication. In particular, generative models of natural language text. Loosely, these works (invertibly) encode message-carrying bits into a sequence of samples from the model, ultimately yielding a plausible natural language covertext. By focusing on this narrow steganographic piece, prior work has largely ignored the significant algorithmic challenges, and performance-security tradeoffs, that arise when one actually tries to build a messaging pipeline around it. We make these challenges concrete, by considering the natural application of such a pipeline: namely, "dead-drop" covert messaging over large, public internet platforms (e.g. social media sites). We explicate the challenges and describe approaches to overcome them, surfacing in the process important performance and security tradeoffs that must be carefully tuned. We implement a system around this model-based format-transforming encryption pipeline, and give an empirical analysis of its performance and (heuristic) security.