Efficient Provably Secure Linguistic Steganography via Range Coding
2026-04-09 • Computation and Language
Computation and LanguageCryptography and Security
AI summaryⓘ
The authors worked on hiding secret messages inside normal texts using language models, a technique called linguistic steganography. They aimed to make this hiding method very secure while keeping it efficient so you can hide a lot of information. They used a coding method called range coding and added a rotation trick to improve performance. Their experiments showed their method uses the encoding capacity fully and works faster than previous methods. They also shared their code online for others to use.
linguistic steganographyprovable securitylanguage modelsKullback-Leibler divergenceentropy codingrange codingembedding capacityembedding efficiencysecret communicationGPT-2
Authors
Ruiyi Yan, Yugo Murawaki
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.