后续扩展与可靠性
Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
首次 arXiv 提交： · EMNLP 2025
正式发表版本：2025年11月。
研究生成词元序列与接收方对可见文本重新分词所得序列之间的不一致。论文为隐写提出逐步验证，为水印检测提出事后回退，并评估可靠性、文本质量和检测表现。
与 Neural Linguistic Steganography 的关系
第 4.1 节明确说明，全部隐写实验都采用 Ziegler 等人的算术编码方法。该工作扩展 2019 年方法周围的可靠性环节，保留其编码原理。
适用范围与边界
隐写提取实验假设攻击者不修改文本。作者报告，水印实验中的不一致词元较少，因此改进幅度较小；分词不一致机制的完整理论仍未建立。
引用这篇论文
正式发表版本
Ruiyi Yan, Yugo Murawaki. Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
正式发表版本 BibTeX · 正式发表版本 CSL-JSON
显示 BibTeX
@inproceedings{tokenization-publication,
title = {{Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models}},
author = {Yan, Ruiyi and Murawaki, Yugo},
year = {2025},
booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
doi = {10.18653/v1/2025.emnlp-main.361},
pages = {7076--7098},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2025.emnlp-main.361/}
}
arXiv 预印本
Ruiyi Yan, Yugo Murawaki. Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models. arXiv:2508.20718。首次提交：2025年8月28日。
该引用保留首个 arXiv 版本及其原始标题。版本链接区分后续修订；请引用支持所述结论的版本。
arXiv 预印本 BibTeX · arXiv 预印本 CSL-JSON
显示 BibTeX
@misc{tokenization-preprint,
title = {{Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models}},
author = {Yan, Ruiyi and Murawaki, Yugo},
year = {2025},
publisher = {arXiv},
eprint = {2508.20718v1},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2508.20718v1}
}