mlsanityData to 14 Oct 2026

Provably Secure Generative Linguistic Steganography

arXiv 2106.02011 ↗First posted 3 Jun 2021cs.CL cs.CRcited by 34

Not on the map. Why?

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.

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

8 of 37 references.

References · 8

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2014Distributed Representations of Sentences and Documentscited by 678
  4. 2019Neural Linguistic Steganographycited by 78
  5. 2017Generating Steganographic Text with LSTMscited by 44
  6. 2019Towards Near-imperceptible Steganographic Textcited by 32
  7. 2018Automatically Generate Steganographic Text Based on Markov Model and Huffman Codingcited by 7
  8. 2014An Approach for Text Steganography Based on Markov Chainscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 1; 2024: 5; 2025: 10; 2026: 11.

34 papers.

Sort:

By area:

  1. 2022Perfectly Secure Steganography Using Minimum Entropy Couplingcited by 44
  2. 2024Generative Text Steganography with Large Language Modelcited by 17
  3. 2025The Steganographic Potentials of Language Modelscited by 10
  4. 2025Are Robust LLM Fingerprints Adversarially Robust?cited by 8
  5. 2022Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Codingcited by 7
  6. 2022Addressing Segmentation Ambiguity in Neural Linguistic Steganographycited by 7
  7. 2025ImF: Implicit Fingerprint for Large Language Modelscited by 7
  8. 2024Provably Secure Disambiguating Neural Linguistic Steganographycited by 5
  9. 2024OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributionscited by 5
  10. 2024Zero-shot Generative Linguistic Steganographycited by 4
  11. 2023UP4LS: User Profile Constructed by Multiple Attributes for Enhancing Linguistic Steganalysiscited by 3
  12. 2024Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheelcited by 3
22 more
  1. 2026Efficient Provably Secure Linguistic Steganography via Range Codingcited by 3
  2. 2021Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deploymentscited by 2
  3. 2025Provable Secure Steganography Based on Adaptive Dynamic Samplingcited by 2
  4. 2025Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganographycited by 2
  5. 2026Invisible Safety Threat: Malicious Finetuning for LLM via Steganographycited by 2
  6. 2026Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganographycited by 2
  7. 2022General Framework for Reversible Data Hiding in Texts Based on Masked Language Modelingcited by 1
  8. 2025GTSD: Generative Text Steganography Based on Diffusion Modelcited by 1
  9. 2025GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysiscited by 1
  10. 2025A High-Capacity and Secure Disambiguation Algorithm for Neural Linguistic Steganographycited by 1
  11. 2025A high-capacity linguistic steganography based on entropy-driven rank-token mappingcited by 1
  12. 2025A Content-Preserving Secure Linguistic Steganographycited by 1
  13. 2026Steganography Without Modification: Hidden Communication via LLM Seedscited by 1
  14. 2026HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Frameworkcited by 1
  15. 2021Pixel-Stega: Generative Image Steganography Based on Autoregressive Modelscited by 0
  16. 2022On Information Hiding in Natural Language Systemscited by 0
  17. 2026Verifier-Bound Communication for LLM Agents: Certified Bounds on Covert Signalingcited by 0
  18. 2026Text Steganography with Dynamic Codebook and Multimodal Large Language Modelcited by 0
  19. 2026REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysiscited by 0
  20. 2026FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysiscited by 0
  21. 2026A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challengescited by 0
  22. 2026CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encodingcited by 0