A Plug-and-Play Method for Improving Imperceptibility and Capacity in Practical Generative Text Steganography

Computer Science > Cryptography and Security [Submitted on 27 Dec 2024 (v1), last revised 26 Jun 2026 (this version, v5)] A Plug-and-Play Method for Improving Imperceptibility and Capacity in Practical Generative Text Steganography Kaiyi Pang Linguistic steganography embeds secret information into seemingly innocuous text to safeguard privacy under surveillance. Generative linguistic steganography leverages the probability distributions of language models (LMs) and applies steganographic algorithms during generation, and has attracted increasing attention with the rise of large language models (LLMs). To strengthen security, prior work has focused on distribution-preserving steganographic algorithms that minimize the gap between stego sampling and random sampling from the model. However, their reliance on model distributions, which often deviate from real-world cover texts, leads to limited imperceptibility when facing steganalysis detectors in practical settings. Moreover, LLM distributions tend to be more deterministic, reducing entropy and thus lowering embedding capacity. In this paper, we propose a plug-and-play method that reconstructs the distributions of language models used for generative linguistic steganography. FreStega dynamically adjusts token probabilities from the language model at each step of autoregressive stego text generation, leveraging both sequential and spatial dimensions. Extensive experiments on four LLMs, three benchmark datasets, and four distribution-preserving steganographic baselines demonstrate that, by reforming the distribution, FreStega improves the imperceptibility of stego text in realistic scenarios and increases steganographic capacity by 15.41\%, without degrading the quality of the generated stegotext. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2412.19652 [cs.CR]   (or arXiv:2412.19652v5 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2412.19652 Focus to learn more Submission history From: Kaiyi Pang [view email] [v1] Fri, 27 Dec 2024 13:56:51 UTC (4,387 KB) [v2] Mon, 30 Dec 2024 07:49:13 UTC (4,410 KB) [v3] Sun, 11 May 2025 13:48:52 UTC (5,372 KB) [v4] Sun, 21 Dec 2025 12:33:28 UTC (5,430 KB) [v5] Fri, 26 Jun 2026 14:08:06 UTC (2,077 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2024-12 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)