Search papers, labs, and topics across Lattice.
The paper introduces ReTokSync, a novel framework for generative linguistic steganography that addresses the vulnerability of tokenization ambiguity, where different tokenizations at sender and receiver break the decoding process. ReTokSync monitors receiver-side tokenization and selectively triggers corrective resets only when ambiguity arises, minimizing disruption to the generation distribution. Experiments on English and Chinese demonstrate that ReTokSync maintains high distributional security, text quality, embedding capacity, and runtime performance, achieving near-perfect extraction accuracy and enabling a two-channel covert communication mechanism with 100% end-to-end recovery.
Achieve near-perfect covert communication even when tokenizers disagree, by selectively patching up tokenization mismatches on the fly.
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.
