mlsanityData to 7 Oct 2026

Neural Linguistic Steganography

arXiv 1909.01496 ↗First posted 3 Sep 2019cs.CL cs.CR cs.LGcited by 73

Not on the map. Why?

Abstract (arXiv)

Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal. Language is a particularly pragmatic cover signal due to its benign occurrence and independence from any one medium. Traditionally, linguistic steganography systems encode secret messages in existing text via synonym substitution or word order rearrangements. Advances in neural language models enable previously impractical generation-based techniques. We propose a steganography technique based on arithmetic coding with large-scale neural language models. We find that our approach can generate realistic looking cover sentences as evaluated by humans, while at the same time preserving security by matching the cover message distribution with the language model distribution.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 15; 2024: 12; 2025: 15; 2026: 21.

73 papers.

Sort:

By area:

  1. 2023A Watermark for Large Language Modelscited by 667
  2. 2023Robust Distortion-free Watermarks for Language Modelscited by 279
  3. 2023On the Reliability of Watermarks for Large Language Modelscited by 170
  4. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 107
  5. 2025Subliminal Learning: Language models transmit behavioral traits via hidden signals in datacited by 89
  6. 2024Watermark Stealing in Large Language Modelscited by 79
  7. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  8. 2023Robust Multi-bit Natural Language Watermarking through Invariant Featurescited by 76
  9. 2023A Survey on Detection of LLMs-Generated Contentcited by 70
  10. 2023Mark My Words: Analyzing and Evaluating Language Model Watermarkscited by 62
  11. 2024Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMscited by 52
  12. 2023Advancing Beyond Identification: Multi-bit Watermark for Large Language Modelscited by 51
38 more
  1. 2022Perfectly Secure Steganography Using Minimum Entropy Couplingcited by 42
  2. 2024AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Textcited by 40
  3. 2023Smaller Language Models are Better Black-box Machine-Generated Text Detectorscited by 35
  4. 2021Provably Secure Generative Linguistic Steganographycited by 34
  5. 2021Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Modelcited by 28
  6. 2023Towards Possibilities & Impossibilities of AI-generated Text Detection: A Surveycited by 28
  7. 2023Embarrassingly Simple Text Watermarkscited by 23
  8. 2023Optimizing watermarks for large language modelscited by 22
  9. 2023Watermarking LLMs with Weight Quantizationcited by 19
  10. 2025BiMark: Unbiased Multilayer Watermarking for Large Language Modelscited by 18
  11. 2023G3Detector: General GPT-Generated Text Detectorcited by 17
  12. 2024Generative Text Steganography with Large Language Modelcited by 16
  13. 2023Source Attribution for Large Language Model-Generated Datacited by 11
  14. 2024Watermarking Language Models with Error Correcting Codescited by 10
  15. 2025Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attackscited by 8
  16. 2022Addressing Segmentation Ambiguity in Neural Linguistic Steganographycited by 7
  17. 2025TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agentcited by 7
  18. 2021Exploiting Language Model for Efficient Linguistic Steganalysiscited by 6
  19. 2022Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Codingcited by 6
  20. 2022Autoregressive Linguistic Steganography Based on BERT and Consistency Codingcited by 6
  21. 2024Provably Secure Disambiguating Neural Linguistic Steganographycited by 5
  22. 2024OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributionscited by 5
  23. 2025ImF: Implicit Fingerprint for Large Language Modelscited by 5
  24. 2026Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systemscited by 5
  25. 2024Zero-shot Generative Linguistic Steganographycited by 4
  26. 2025Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)cited by 3
  27. 2025Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Modelscited by 3
  28. 2026Efficient Provably Secure Linguistic Steganography via Range Codingcited by 3
  29. 2021Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deploymentscited by 2
  30. 2024Large Language Models as Carriers of Hidden Messagescited by 2
  31. 2024Steganography in Game Actionscited by 2
  32. 2025Provable Secure Steganography Based on Adaptive Dynamic Samplingcited by 2
  33. 2025LLMs can hide text in other text of the same lengthcited by 2
  34. 2026Invisible Safety Threat: Malicious Finetuning for LLM via Steganographycited by 2
  35. 2026Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganographycited by 2
  36. 2026An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egresscited by 2
  37. 2024Task-Oriented Paraphrase Analyticscited by 1
  38. 2025Steganography Beyond Space-Time with Chain of Multimodal AIcited by 1

50 most cited of 73 All 73 (JSON)