$\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models

• URL: http://arxiv.org/abs/2511.05319v1
• Date: Fri, 07 Nov 2025 15:17:40 GMT
• Title: $\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models
• Authors: Huanqi Wu, Huangbiao Xu, Runfeng Xie, Jiaxin Cai, Kaixin Zhang, Xiao Ke,
• Abstract summary: Sentence-to-Image Steganography is a novel task that enables the hiding of arbitrary sentence-level messages within a cover image.<n>Semantic Steganographic Language Model embeds high-level textual information, such as sentences or even paragraphs, into images.<n>$mathrmS2LM$ enables the integration of semantically rich content through a newly designed pipeline.
• Score: 12.563873091938364
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Although steganography has made significant advancements in recent years, it still struggles to embed semantically rich, sentence-level information into carriers. However, in the era of AIGC, the capacity of steganography is more critical than ever. In this work, we present Sentence-to-Image Steganography, an instance of Semantic Steganography, a novel task that enables the hiding of arbitrary sentence-level messages within a cover image. Furthermore, we establish a benchmark named Invisible Text (IVT), comprising a diverse set of sentence-level texts as secret messages for evaluation. Finally, we present $\mathbf{S^2LM}$: Semantic Steganographic Language Model, which utilizes large language models (LLMs) to embed high-level textual information, such as sentences or even paragraphs, into images. Unlike traditional bit-level counterparts, $\mathrm{S^2LM}$ enables the integration of semantically rich content through a newly designed pipeline in which the LLM is involved throughout the entire process. Both quantitative and qualitative experiments demonstrate that our method effectively unlocks new semantic steganographic capabilities for LLMs. The source code will be released soon.

Related papers

• VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning [49.28966310502341]
  Few-shot learning aims to recognize novel concepts from only a few labeled support samples.<n>Recent studies enhance support features by incorporating additional semantic information or designing complex semantic fusion modules.<n>We propose a novel framework, bridging Vision and Text with Large Language Models for Few-Shot Learning.
  arXiv  Detail & Related papers  (2025-09-29T16:52:47Z)
• Semantic Steganography: A Framework for Robust and High-Capacity Information Hiding using Large Language Models [25.52890764952079]
  generative linguistic steganography has become a prevalent technique for hiding information within model-generated texts.<n>We propose a semantic steganography framework based on Large Language Models (LLMs)<n>This framework offers robustness and reliability for transmission in complex channels, as well as resistance to text rendering and word blocking.
  arXiv  Detail & Related papers  (2024-12-15T04:04:23Z)
• Generative Text Steganography with Large Language Model [10.572149957139736]
  Black-box generative text steganographic method based on user interfaces of large language models, which is called LLM-Stega. We first construct a keyword set and design a new encrypted steganographic mapping to embed secret messages. Comprehensive experiments demonstrate that the proposed LLM-Stega outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-04-16T02:19:28Z)
• Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics [50.982315553104975]
  We investigate the bottom-up evolution of lexical semantics for a popular large language model, namely Llama2. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics.
  arXiv  Detail & Related papers  (2024-03-03T13:14:47Z)
• Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel [10.72286166021398]
  Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool.<n>This paper proposes a scheme based on the interval allocated, called DAIRstega.
  arXiv  Detail & Related papers  (2024-01-28T13:21:44Z)
• Large Language Models on Graphs: A Comprehensive Survey [77.16803297418201]
  We provide a systematic review of scenarios and techniques related to large language models on graphs. We first summarize potential scenarios of adopting LLMs on graphs into three categories, namely pure graphs, text-attributed graphs, and text-paired graphs. We discuss the real-world applications of such methods and summarize open-source codes and benchmark datasets.
  arXiv  Detail & Related papers  (2023-12-05T14:14:27Z)
• Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation [53.97962603641629]
  We propose a novel mulTi-source sEmantic grAph-based Multimodal sarcasm explanation scheme, named TEAM. TEAM extracts the object-level semantic meta-data instead of the traditional global visual features from the input image. TEAM introduces a multi-source semantic graph that comprehensively characterize the multi-source semantic relations.
  arXiv  Detail & Related papers  (2023-06-29T03:26:10Z)
• Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning [51.90524745663737]
  A key innovation is our use of explanations as features, which can be used to boost GNN performance on downstream tasks. Our method achieves state-of-the-art results on well-established TAG datasets. Our method significantly speeds up training, achieving a 2.88 times improvement over the closest baseline on ogbn-arxiv.
  arXiv  Detail & Related papers  (2023-05-31T03:18:03Z)
• A Survey On Semantic Steganography Systems [0.0]
  Steganography is the practice of concealing a message within some other carrier or cover message. In semantic steganography, redundancies in the semantics of a language are used to send a text steganographic message. We list systems for semantic steganography that have been published in the past and review their properties.
  arXiv  Detail & Related papers  (2022-02-03T15:23:53Z)
• Revisiting Self-Training for Few-Shot Learning of Language Model [61.173976954360334]
  Unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
  arXiv  Detail & Related papers  (2021-10-04T08:51:36Z)

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.