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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Huanqi, Xu, Huangbiao, Xie, Runfeng, Cai, Jiaxin, Zhang, Kaixin, Ke, Xiao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912805513330688
author Wu, Huanqi
Xu, Huangbiao
Xie, Runfeng
Cai, Jiaxin
Zhang, Kaixin
Ke, Xiao
author_facet Wu, Huanqi
Xu, Huangbiao
Xie, Runfeng
Cai, Jiaxin
Zhang, Kaixin
Ke, Xiao
contents Despite remarkable progress in steganography, embedding semantically rich, sentence-level information into carriers remains a challenging problem. In this work, we present a novel concept of Semantic Steganography, which aims to hide semantically meaningful and structured content, such as sentences or paragraphs, in cover media. Based on this concept, we present Sentence-to-Image Steganography as an instance that enables the hiding of arbitrary sentence-level messages within a cover image. To accomplish this feat, we propose S^2LM: Semantic Steganographic Language Model, which leverages large language models (LLMs) to embed high-level textual information into images. Unlike traditional bit-level approaches, S^2LM redesigns the entire pipeline, involving the LLM throughout the process to enable the hiding and recovery of arbitrary sentences. Furthermore, we establish a benchmark named Invisible Text (IVT), comprising a diverse set of sentence-level texts as secret messages to evaluate semantic steganography methods. Experimental results demonstrate that S^2LM effectively enables direct sentence recovery beyond bit-level steganography. The source code and IVT dataset will be released soon.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05319
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle $\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models
Wu, Huanqi
Xu, Huangbiao
Xie, Runfeng
Cai, Jiaxin
Zhang, Kaixin
Ke, Xiao
Computer Vision and Pattern Recognition
Cryptography and Security
Despite remarkable progress in steganography, embedding semantically rich, sentence-level information into carriers remains a challenging problem. In this work, we present a novel concept of Semantic Steganography, which aims to hide semantically meaningful and structured content, such as sentences or paragraphs, in cover media. Based on this concept, we present Sentence-to-Image Steganography as an instance that enables the hiding of arbitrary sentence-level messages within a cover image. To accomplish this feat, we propose S^2LM: Semantic Steganographic Language Model, which leverages large language models (LLMs) to embed high-level textual information into images. Unlike traditional bit-level approaches, S^2LM redesigns the entire pipeline, involving the LLM throughout the process to enable the hiding and recovery of arbitrary sentences. Furthermore, we establish a benchmark named Invisible Text (IVT), comprising a diverse set of sentence-level texts as secret messages to evaluate semantic steganography methods. Experimental results demonstrate that S^2LM effectively enables direct sentence recovery beyond bit-level steganography. The source code and IVT dataset will be released soon.
title $\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2511.05319