Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel

TL;DR

DAIRstega is a novel linguistic steganography method that uses a roulette wheel approach based on token conditional probabilities to improve concealment quality and controllability in generated stegos.

Contribution

It introduces a dynamic interval allocation scheme using CPs for better token selection, enhancing stego quality and security over existing methods.

Findings

Outperforms existing steganography schemes in perceptual and statistical tests.

Supports controllable, prompt-based generation of high-quality stegos.

Demonstrates strong anti-steganalysis and potential for secure watermarking.

Abstract

Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool, allocating the one coding to all tokens, which results in identical selection likelihoods. This approach leads to the selection of low-CP tokens, degrading the quality of stegos and making them more detectable. This paper proposes a scheme based on the interval allocated, called DAIRstega. DAIRstega first uses a portion of the read secret to build the roulette area. Then, this scheme uses the idea of the roulette wheel and takes the CPs of tokens as the main basis for allocating the roulette area (i.e., the interval length). Thus, tokens with larger CPs are allocated more area. The secret will have an increased likelihood of selecting a token with a higher CP. During allocation, we designed some allocation functions and three constraints to optimize the process. Additionally, DAIRstega supports prompt-based controllable generation of stegos. Rich experiments show that the proposed embedding way and DAIRstega perform better than the existing ways and baselines, which shows strong perceptual, statistical, and semantic concealment, as well as anti-steganalysis ability. It can also generate high-quality longer stegos, addressing the deficiencies in this task. DAIRstega is confirmed to have potential as a secure watermarking, offering insights for its development.