A high-capacity linguistic steganography based on entropy-driven rank-token mapping

TL;DR

This paper introduces RTMStega, a novel entropy-driven linguistic steganography framework that significantly enhances payload capacity and efficiency while maintaining high text quality for covert communication.

Contribution

The paper presents a new entropy-driven approach with rank-based adaptive coding and context-aware adjustments, improving capacity and security over existing methods.

Findings

Triples payload capacity of existing steganography methods

Reduces processing time by over 50%

Maintains high text quality in generated stego texts

Abstract

Linguistic steganography enables covert communication through embedding secret messages into innocuous texts; however, current methods face critical limitations in payload capacity and security. Traditional modification-based methods introduce detectable anomalies, while retrieval-based strategies suffer from low embedding capacity. Modern generative steganography leverages language models to generate natural stego text but struggles with limited entropy in token predictions, further constraining capacity. To address these issues, we propose an entropy-driven framework called RTMStega that integrates rank-based adaptive coding and context-aware decompression with normalized entropy. By mapping secret messages to token probability ranks and dynamically adjusting sampling via context-aware entropy-based adjustments, RTMStega achieves a balance between payload capacity and imperceptibility. Experiments across diverse datasets and models demonstrate that RTMStega triples the payload capacity of mainstream generative steganography, reduces processing time by over 50%, and maintains high text quality, offering a trustworthy solution for secure and efficient covert communication.