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

arXiv:2511.05319v3 Announce Type: replace Abstract: Despite remarkable progress in steganography, embedding sentence-level information into cover media remains challenging. In this work, we present the concept of extbf{Semantic-Payload Steganography}, which aims to hide semantically meaningful and structured content, such as sentences, in cover media. Based on this concept, we present Sentence-to-Image Steganography as an instance that enables the hiding of sentence-level messages within a cover image. To accomplish this feat, we propose extbf{S}emantic-Payload extbf{S}teganographic extbf{L}anguage extbf{M}odel (mathbf{S^2LM}), which leverages large language models to embed high-level textual information into images. mathbf{S^2LM} redesigns the entire pipeline, involving the LLM throughout the process to enable the hiding and recovery of sentences. To evaluate semantic-payload steganography methods, we establish a benchmark named extbf{I}nextbf{v}isible extbf{T}ext (IVT), comprising a diverse set of corpus as secret messages. Experimental results demonstrate that mathbf{S^2LM} effectively recovers natural-language messages while maintaining high visual quality. The source code will be released at https://github.com/aoli-gei/S2LM.

Source: arXiv cs.CV | 2026-10-14