ADLM -- stega: A Universal Adaptive Token Selection Algorithm for Improving Steganographic Text Quality via Information Entropy

TL;DR

This paper introduces ADLM--stega, an adaptive token selection algorithm that improves the quality and imperceptibility of steganographic texts by controlling information entropy during generation.

Contribution

It proposes a novel entropy-based quality control method with adaptive token selection to enhance steganographic text imperceptibility and robustness.

Findings

Controlling information entropy improves text quality.

Adaptive token selection balances coherence and diversity.

Enhanced detection resistance of steganographic texts.

Abstract

In the context of widespread global information sharing, information security and privacy protection have become focal points. Steganographic systems enhance information security by embedding confidential information into public carriers; however, existing generative text steganography methods face challenges in handling the long-tail distribution of candidate word pools, which impacts the imperceptibility of steganographic information. This paper proposes a quality control theory for steganographic text generation based on information entropy constraints, exploring the relationship between the imperceptibility of steganographic texts and information entropy. By controlling the information entropy of the candidate word pool within a specific range, we optimize the imperceptibility of the steganographic text. We establish upper and lower bounds for information entropy and introduce an adaptive truncation method to balance semantic coherence and lexical diversity. Experimental results demonstrate that reasonably controlling the candidate pool size and information entropy thresholds significantly enhances the quality and detection resistance of steganographic texts, showcasing broad application potential in the field of natural language processing.