Recent advances in large language models (LLMs) have blurred the boundary of high-quality text generation between humans and machines, which is favorable for generative text steganography. While, current advanced steganographic mapping is not suitable for LLMs since most users are restricted to accessing only the black-box API or user interface of the LLMs, thereby lacking access to the training vocabulary and its sampling probabilities. In this paper, we explore a black-box generative text steganographic method based on the user interfaces of large language models, which is called LLM-Stega. The main goal of LLM-Stega is that the secure covert communication between Alice (sender) and Bob (receiver) is conducted by using the user interfaces of LLMs. Specifically, We first construct a keyword set and design a new encrypted steganographic mapping to embed secret messages. Furthermore, to guarantee accurate extraction of secret messages and rich semantics of generated stego texts, an optimization mechanism based on reject sampling is proposed. Comprehensive experiments demonstrate that the proposed LLM-Stega outperforms current state-of-the-art methods.

翻译：近期大型语言模型（LLMs）的进展模糊了人机高质量文本生成的界限，这有利于生成式文本隐写术的发展。然而，当前先进隐写映射方法不适用于LLMs，因为大多数用户仅能通过黑盒API或用户界面访问LLMs，无法获取训练词汇表及其采样概率。本文探索了一种基于大型语言模型用户界面的黑盒生成式文本隐写方法，称为LLM-Stega。该方法的核心目标是利用LLMs的用户界面实现Alice（发送方）与Bob（接收方）之间的安全隐蔽通信。具体而言，我们首先构建关键词集合，设计新型加密隐写映射以嵌入秘密信息。此外，为保证秘密信息的准确提取与生成隐写文本的语义丰富性，提出基于拒绝采样的优化机制。综合实验表明，所提出的LLM-Stega方法优于当前最先进方法。