ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography

TL;DR

ReTokSync is a novel self-synchronizing framework for linguistic steganography that effectively manages tokenization ambiguity, ensuring high security, quality, and near-perfect message extraction in covert language communication.

Contribution

It introduces ReTokSync, a disambiguation method that maintains synchronization during generation, improving security and efficiency over existing solutions.

Findings

ReTokSync achieves over 99.7% extraction accuracy.

It maintains zero KL divergence, indicating distributional security.

The two-channel system ensures 100% end-to-end message recovery.

Abstract

Generative linguistic steganography (GLS) enables covert communication by embedding secret messages into the natural language generation process. In practical deployment, however, GLS is vulnerable to tokenization ambiguity: the same surface text may be re-tokenized into a different token sequence at the receiver, breaking the shared decoding state between the communicating parties so that a single local mismatch can propagate into complete extraction failure. Existing solutions either remove ambiguous tokens -- distorting the generation distribution and compromising security -- or preserve the distribution at the cost of substantially reduced embedding capacity or prohibitive runtime overhead. To address this issue, we propose ReTokSync (Re-Tokenization Synchronization), a self-synchronizing disambiguation framework that monitors the receiver-view tokenization during generation and triggers a corrective reset only when ambiguity actually occurs. By confining the effect of tokenization ambiguity to sparse residual bit errors rather than global desynchronization, ReTokSync leaves ambiguity-free positions entirely untouched and remains compatible with the underlying steganographic algorithm. Experiments on both English and Chinese settings show that ReTokSync stays closest to the steganographic baseline in distributional security (zero KL divergence), text quality, embedding capacity, and runtime, while achieving extraction accuracy above 99.7\%. Building on this property, we further develop a two-channel covert communication mechanism in which ReTokSync serves as the primary channel and a reliable auxiliary channel corrects the remaining errors, achieving 100\% end-to-end recovery across all evaluated configurations.