S 2LM: Towards Semantic Steganography via Large Language Models

Despite remarkable progress in steganography, embedding sentence-level information into cover media remains challenging. In this work, we present the concept of 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 Semantic-Payload Steganographic Language Model (S 2LM), which leverages large language models to embed high-level textual information into images. 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 In visible Text (IVT), comprising a diverse set of corpus as secret messages. Experimental results demonstrate that 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.