mlsanityData to 14 Oct 2026

A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges

arXiv 2608.29077 ↗First posted 29 Aug 2026cs.CR cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Linguistic steganography hides secret messages in natural language text. Large language models (LLMs) have reshaped the field, but a systematic account of how these scattered advances collectively reshape the field in this new era is still missing. We provide one along four axes: 148 steganographic methods, 60 linguistic steganalysis countermeasures, 23 evaluation metrics, and 9 open challenges, each with taxonomies, reviews, and adoption analyses. Cutting across these axes, we identify five specific paradigm shifts in the LLM era: (1) from covertext modification to prompt-only generation, (2) from heuristic to provable security, (3) from white-box symmetric LMs to black-box or asymmetric access, (4) from security-centric designs to joint optimization, and (5) from text-quality concerns to engineering issues. The survey aims to serve as both a reference and a roadmap for practical and responsible linguistic steganography in the LLM era.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 230 references that are in the map. First posted on arXiv 29 Aug 2026.

Builds on

41 of 230 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  5. 2024A Survey on LLM-as-a-Judgecited by 1,423
  6. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  7. 2014Distributed Representations of Sentences and Documentscited by 678
  8. 2019ERNIE: Enhanced Representation through Knowledge Integrationcited by 302
  9. 2024Non-Determinism of "Deterministic" LLM Settingscited by 92
  10. 2019Neural Linguistic Steganographycited by 78
  11. 2017Generating Steganographic Text with LSTMscited by 44
  12. 2022Perfectly Secure Steganography Using Minimum Entropy Couplingcited by 44
29 more
  1. 2021Provably Secure Generative Linguistic Steganographycited by 34
  2. 2019Towards Near-imperceptible Steganographic Textcited by 32
  3. 2021Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Modelcited by 30
  4. 2024The Model Openness Framework: Promoting Completeness and Openness for Reproducibility, Transparency, and Usability in Artificial Intelligencecited by 23
  5. 2019TS-RNN: Text Steganalysis Based on Recurrent Neural Networkscited by 20
  6. 2020Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Codingcited by 17
  7. 2025SparSamp: Efficient Provably Secure Steganography Based on Sparse Samplingcited by 14
  8. 2018Automatically Generate Steganographic Text Based on Markov Model and Huffman Codingcited by 7
  9. 2022Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Codingcited by 7
  10. 2022Addressing Segmentation Ambiguity in Neural Linguistic Steganographycited by 7
  11. 2021Exploiting Language Model for Efficient Linguistic Steganalysiscited by 6
  12. 2022Autoregressive Linguistic Steganography Based on BERT and Consistency Codingcited by 6
  13. 2024Provably Robust and Secure Steganography in Asymmetric Resource Scenariocited by 6
  14. 2024Towards Next-Generation Steganalysis: LLMs Unleash the Power of Detecting Steganographycited by 5
  15. 2024Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheelcited by 3
  16. 2026Efficient Provably Secure Linguistic Steganography via Range Codingcited by 3
  17. 2020Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graphcited by 2
  18. 2024Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysiscited by 2
  19. 2025Provable Secure Steganography Based on Adaptive Dynamic Samplingcited by 2
  20. 2025Provably Secure Public-Key Steganography Based on Admissible Encodingcited by 2
  21. 2026STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Modelcited by 2
  22. 2026Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganographycited by 2
  23. 2022General Framework for Reversible Data Hiding in Texts Based on Masked Language Modelingcited by 1
  24. 2023ICStega: Image Captioning-based Semantically Controllable Linguistic Steganographycited by 1
  25. 2024ADLM -- stega: A Universal Adaptive Token Selection Algorithm for Improving Steganographic Text Quality via Information Entropycited by 1
  26. 2025GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysiscited by 1
  27. 2025A High-Capacity and Secure Disambiguation Algorithm for Neural Linguistic Steganographycited by 1
  28. 2025A Content-Preserving Secure Linguistic Steganographycited by 1
  29. 2026HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Frameworkcited by 1

Built on by

Not cited yet.