ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography

Computer Science > Cryptography and Security [Submitted on 28 Apr 2026] ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography Yaofei Wang, Rui Wang, Weilong Pang, JiaLiang Han, Yuan Qi, Donghui Hu, Kejiang Chen 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. Comments: 20 pages, 5 figures Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2604.25486 [cs.CR]   (or arXiv:2604.25486v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.25486 Focus to learn more Submission history From: Rui Wang [view email] [v1] Tue, 28 Apr 2026 10:42:43 UTC (1,072 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)