paper-with-me

홈 › Papers

Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel

2024-01-28 · Yihao Wang, Ruiqi Song, Lingxiao Li, Ru Zhang, Jianyi Liu

Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool, allocating the one coding to all tokens, which results in identical selection likelihoods. This approach leads to the selection of low-CP tokens, degrading the quality of stegos and making them more detectable. This paper proposes a scheme based on the interval allocated, called DAIRstega. DAIRstega first uses a portion of the read secret to build the roulette area. Then, this scheme uses the idea of the roulette wheel and takes the CPs of tokens as the main basis for allocating the roulette area (i.e., the interval length). Thus, tokens with larger CPs are allocated more area. The secret will have an increased likelihood of selecting a token with a higher CP. During allocation, we designed some allocation functions and three constraints to optimize the process. Additionally, DAIRstega supports prompt-based controllable generation of stegos. Rich experiments show that the proposed embedding way and DAIRstega perform better than the existing ways and baselines, which shows strong perceptual, statistical, and semantic concealment, as well as anti-steganalysis ability. It can also generate high-quality longer stegos, addressing the deficiencies in this task. DAIRstega is confirmed to have potential as a secure watermarking, offering insights for its development.

📄 PDF Abstract BibTeX arXiv:2401.15656

Code (1)

wangyh-bupt/dairstega 공식 구현 pytorch

Tasks

Language ModellingLarge Language ModelLinguistic steganographySteganalysis

Similar Papers 제목 키워드 기반

A high-capacity linguistic steganography based on entropy-driven rank-token mapping

2025-10-27 · Jun Jiang, Weiming Zhang, Nenghai Yu, Kejiang Chen arxiv

Linguistic steganography enables covert communication through embedding secret messages into innocuous texts; however, current methods face critical limitations in payload capacity and security. Traditional modification-…

Zero-shot Generative Linguistic Steganography

2024-03-16 · Ke Lin, Yiyang Luo, Zijian Zhang, Ping Luo

Generative linguistic steganography attempts to hide secret messages into covertext. Previous studies have generally focused on the statistical differences between the covertext and stegotext, however, ill-formed stegote…

In-Context LearningLinguistic steganography

FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis

2026-06-03 · Shuo Liu, Xianghong Lin, Yukun Wei, Zhongliang Yang arxiv

The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. However, detection is severely hampered by two fundamental issues during model training. Firstly, …

Provably Secure Generative Linguistic Steganography

2021-06-03 · Findings (ACL) 2021 8 · Siyu Zhang, Zhongliang Yang, Jinshuai Yang, Yongfeng Huang

Generative linguistic steganography mainly utilized language models and applied steganographic sampling (stegosampling) to generate high-security steganographic text (stegotext). However, previous methods generally lead …

Language ModelingLanguage ModellingLinguistic steganography

A Secure and Disambiguating Approach for Generative Linguistic Steganography

2023-08-11 · IEEE Signal Processing Letters 2023 8 · Ruiyi Yan, Yating Yang, Tian Song

Segmentation ambiguity in generative linguistic steganography could induce decoding errors. One existing disambiguating way is removing the tokens whose mapping words are the prefixes of others in each candidate pool. Ho…

Linguistic steganographySegmentationSteganalysis