$\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models
This addresses the need for higher-capacity steganography in the AIGC era, enabling hiding of arbitrary sentence-level information in images, though it appears incremental as it builds on existing LLM and steganography techniques.
The paper tackles the problem of embedding semantically rich, sentence-level messages into images, a challenge in steganography, and introduces S^2LM, a method using large language models to achieve this, with experiments showing it unlocks new semantic steganographic capabilities.
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.