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

TL;DR

This paper introduces S^2LM, a novel semantic steganography method using large language models to embed and recover meaningful sentences within images, surpassing traditional bit-level approaches.

Contribution

We propose S^2LM, a new pipeline leveraging LLMs for semantic embedding in images, and establish the IVT benchmark for evaluating semantic steganography.

Findings

S^2LM enables direct recovery of sentence-level messages.

S^2LM outperforms traditional bit-level steganography methods.

The IVT benchmark provides a diverse dataset for evaluation.

Abstract

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.