Semantic Steganography: A Framework for Robust and High-Capacity Information Hiding using Large Language Models

TL;DR

This paper introduces a semantic steganography framework leveraging large language models to embed secret messages into generated texts, achieving high capacity, robustness, and indistinguishability from cover texts.

Contribution

It presents a novel semantic space construction using ontology-entity trees for robust, high-capacity information hiding with LLMs, outperforming existing methods.

Findings

Higher embedding capacity than state-of-the-art methods

Stegos are indistinguishable from cover texts

Enhanced robustness against text rendering and word blocking

Abstract

In the era of Large Language Models (LLMs), generative linguistic steganography has become a prevalent technique for hiding information within model-generated texts. However, traditional steganography methods struggle to effectively align steganographic texts with original model-generated texts due to the lower entropy of the predicted probability distribution of LLMs. This results in a decrease in embedding capacity and poses challenges for decoding stegos in real-world communication channels. To address these challenges, we propose a semantic steganography framework based on LLMs, which construct a semantic space and map secret messages onto this space using ontology-entity trees. This framework offers robustness and reliability for transmission in complex channels, as well as resistance to text rendering and word blocking. Additionally, the stegos generated by our framework are indistinguishable from the covers and achieve a higher embedding capacity compared to state-of-the-art steganography methods, while producing higher quality stegos.