A Character-based Diffusion Embedding Algorithm for Enhancing the Generation Quality of Generative Linguistic Steganographic Texts

• URL: http://arxiv.org/abs/2505.00977v2
• Date: Wed, 07 May 2025 17:00:28 GMT
• Title: A Character-based Diffusion Embedding Algorithm for Enhancing the Generation Quality of Generative Linguistic Steganographic Texts
• Authors: Yingquan Chen, Qianmu Li, Xiaocong Wu, Huifeng Li, Qing Chang,
• Abstract summary: This paper proposes a novel embedding algorithm, character-based diffusion embedding algorithm (CDEA)<n>It enhances the selection frequency of high-probability candidate words in the candidate pool based on general statistical properties at the character level.<n>It reduces the selection frequency of low-probability candidate words in the candidate pool.<n> Experimental results demonstrate that the combination of CDEA and XLNet significantly improves the quality of generated steganographic text.
• Score: 6.571673823245785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating high-quality steganographic text is a fundamental challenge in the field of generative linguistic steganography. This challenge arises primarily from two aspects: firstly, the capabilities of existing models in text generation are limited; secondly, embedding algorithms fail to effectively mitigate the negative impacts of sensitive information's properties, such as semantic content or randomness. Specifically, to ensure that the recipient can accurately extract hidden information, embedding algorithms often have to consider selecting candidate words with relatively low probabilities. This phenomenon leads to a decrease in the number of high-probability candidate words and an increase in low-probability candidate words, thereby compromising the semantic coherence and logical fluency of the steganographic text and diminishing the overall quality of the generated steganographic material. To address this issue, this paper proposes a novel embedding algorithm, character-based diffusion embedding algorithm (CDEA). Unlike existing embedding algorithms that strive to eliminate the impact of sensitive information's properties on the generation process, CDEA leverages sensitive information's properties. It enhances the selection frequency of high-probability candidate words in the candidate pool based on general statistical properties at the character level and grouping methods based on power-law distributions, while reducing the selection frequency of low-probability candidate words in the candidate pool. Furthermore, to ensure the effective transformation of sensitive information in long sequences, we also introduce the XLNet model. Experimental results demonstrate that the combination of CDEA and XLNet significantly improves the quality of generated steganographic text, particularly in terms of perceptual-imperceptibility.

Related papers

• DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation [2.4555276449137042]
  We propose DiffSampling, a new decoding method that leverages a mathematical analysis of the token probability distribution.<n>Experiments involving four different text-generation tasks demonstrate that our approach consistently performs at least on par with the existing methods.
  arXiv  Detail & Related papers  (2025-02-19T19:00:02Z)
• TextSleuth: Towards Explainable Tampered Text Detection [49.88698441048043]
  We propose to explain the basis of tampered text detection with natural language via large multimodal models.<n>To fill the data gap for this task, we propose a large-scale, comprehensive dataset, ETTD.<n>Elaborate queries are introduced to generate high-quality anomaly descriptions with GPT4o.<n>To automatically filter out low-quality annotations, we also propose to prompt GPT4o to recognize tampered texts.
  arXiv  Detail & Related papers  (2024-12-19T13:10:03Z)
• Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives [0.0]
  We analyze publicly available text narratives of police-public interactions recorded by Boston Police Department.<n>We compare qualitative coding of instruction tuned large language models (IT-LLMs) against human coders.
  arXiv  Detail & Related papers  (2024-12-16T15:27:37Z)
• ADLM -- stega: A Universal Adaptive Token Selection Algorithm for Improving Steganographic Text Quality via Information Entropy [1.413488665073795]
  Steganographic systems enhance information security by embedding confidential information into public carriers. Existing generative text steganography methods face challenges in handling the long-tail distribution of candidate word pools. This paper proposes a quality control theory for steganographic text generation based on information entropy constraints.
  arXiv  Detail & Related papers  (2024-10-28T08:25:31Z)
• Provably Secure Disambiguating Neural Linguistic Steganography [66.30965740387047]
  The segmentation ambiguity problem, which arises when using language models based on subwords, leads to occasional decoding failures.<n>We propose a novel secure disambiguation method named SyncPool, which effectively addresses the segmentation ambiguity problem.<n> SyncPool does not change the size of the candidate pool or the distribution of tokens and thus is applicable to provably secure language steganography methods.
  arXiv  Detail & Related papers  (2024-03-26T09:25:57Z)
• ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection [6.27025292177391]
  ToBlend is a novel token-level ensemble text generation method to challenge the robustness of current AI-content detection approaches. We find ToBlend significantly drops the performance of most mainstream AI-content detection methods.
  arXiv  Detail & Related papers  (2024-02-17T02:25:57Z)
• Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy [52.765898203824975]
  We introduce a semantic-aware watermarking algorithm that considers the characteristics of conditional text generation and the input context. Experimental results demonstrate that our proposed method yields substantial improvements across various text generation models.
  arXiv  Detail & Related papers  (2023-07-25T20:24:22Z)
• An Invariant Learning Characterization of Controlled Text Generation [25.033675230270212]
  Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. We show that the performance of controlled generation may be poor if the distributions of text in response to user prompts differ from the distribution the predictor was trained on.
  arXiv  Detail & Related papers  (2023-05-31T21:35:08Z)
• CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning [14.637303913878435]
  We present a coherence-based contrastive learning model named CoCo to detect the possible MGT under low-resource scenario. To exploit the linguistic feature, we encode coherence information in form of graph into text representation. Experiment results on two public datasets and two self-constructed datasets prove our approach outperforms the state-of-art methods significantly.
  arXiv  Detail & Related papers  (2022-12-20T15:26:19Z)
• An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation [77.44921096644698]
  We present a systematic analysis of the impact of decoding algorithms on LM fairness. We analyze the trade-off between fairness, diversity and quality.
  arXiv  Detail & Related papers  (2022-10-07T21:33:34Z)
• On the probability-quality paradox in language generation [76.69397802617064]
  We analyze language generation through an information-theoretic lens. We posit that human-like language should contain an amount of information close to the entropy of the distribution over natural strings.
  arXiv  Detail & Related papers  (2022-03-31T17:43:53Z)
• Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information [55.75018546938499]
  We propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels. Our method achieves lower diarization error rate than the target-speaker voice activity detection.
  arXiv  Detail & Related papers  (2021-11-28T12:51:04Z)
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification [56.98218530073927]
  Graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are unable to capture high-order interaction between words. We propose a principled model -- hypergraph attention networks (HyperGAT) which can obtain more expressive power with less computational consumption for text representation learning.
  arXiv  Detail & Related papers  (2020-11-01T00:21:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.