Efficient Provably Secure Linguistic Steganography via Range Coding

TL;DR

This paper introduces a new linguistic steganography method using range coding that achieves high embedding capacity and speed while maintaining provable security, outperforming existing approaches.

Contribution

It presents an efficient, provably secure linguistic steganography technique with a rotation mechanism based on range coding, significantly improving capacity and speed.

Findings

Achieves around 100% entropy utilization for embedding capacity.

Attains high embedding speeds up to 1554.66 bits/sec on GPT-2.

Outperforms baseline methods in capacity and speed.

Abstract

Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to language-model-based steganography. Previous provably secure approaches have achieved perfect imperceptibility, measured by zero Kullback-Leibler (KL) divergence, but at the expense of embedding capacity. In this paper, we attempt to directly use a classic entropy coding method (range coding) to achieve secure steganography, and then propose an efficient and provably secure linguistic steganographic method with a rotation mechanism. Experiments across various language models show that our method achieves around 100% entropy utilization (embedding efficiency) for embedding capacity, outperforming the existing baseline methods. Moreover, it achieves high embedding speeds (up to 1554.66 bits/s on GPT-2). The code is available at github.com/ryehr/RRC_steganography.