发表机构
Graduate School of Informatics, Kyoto University; School of Cyberspace Security, Beijing University of Posts and Telecommunications（京都大学信息学研究科; 北京邮电大学网络空间安全学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该综述梳理了LLM时代语言隐写术的148种方法、60种对抗措施等内容，明确五大范式转变，为相关研究提供参考与路线图。
AI 中文摘要
语言隐写术将秘密消息隐藏在自然语言文本中。大语言模型（LLMs）重塑了该领域，但仍缺少对这些分散进展如何在新时代共同重塑该领域的系统阐述。我们从四个维度提供了相关内容：148种隐写方法、60种语言隐写分析对抗措施、23种评估指标和9个开放挑战，每个维度都包含分类、综述和采用分析。跨这些维度，我们确定了LLM时代的五个特定范式转变：（1）从载体文本修改到仅提示生成；（2）从启发式到可证明安全性；（3）从白盒对称语言模型（LMs）到黑盒或非对称访问；（4）从以安全为中心的设计到联合优化；（5）从文本质量问题到工程问题。本综述旨在作为LLM时代实用且负责任的语言隐写术的参考和路线图。
英文摘要
Linguistic steganography hides secret messages in natural language text. Large language models (LLMs) have reshaped the field, but a systematic account of how these scattered advances collectively reshape the field in this new era is still missing. We provide one along four axes: 148 steganographic methods, 60 linguistic steganalysis countermeasures, 23 evaluation metrics, and 9 open challenges, each with taxonomies, reviews, and adoption analyses. Cutting across these axes, we identify five specific paradigm shifts in the LLM era: (1) from covertext modification to prompt-only generation, (2) from heuristic to provable security, (3) from white-box symmetric LMs to black-box or asymmetric access, (4) from security-centric designs to joint optimization, and (5) from text-quality concerns to engineering issues. The survey aims to serve as both a reference and a roadmap for practical and responsible linguistic steganography in the LLM era.
CommentsAccepted by EMNLP 2026
