Abstract
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.
Abstract (translated)
近年来，大型语言模型（LLMs）的进步模糊了高质量文本生成领域人类和机器之间的边界，这对隐式文本加密非常有利。然而，目前的先进隐式映射方法并不适用于LLMs，因为大多数用户只能访问LLMs的黑色盒API或用户界面，而无法访问训练词汇及其抽样概率。在本文中，我们探讨了一种基于LLM用户界面的黑盒生成文本隐式映射方法，称为LLM-Stega。LLM-Stega的主要目标是通过使用LLM的用户界面进行安全隐式通信。具体来说，我们首先构建了一个关键词集，并设计了一个新的隐式文本映射来嵌入秘密消息。此外，为了确保准确提取秘密消息和生成的隐式文本的丰富语义，提出了一个基于拒绝抽样的优化机制。全面的实验证明，与现有技术水平相比，LLM-Stega取得了优异的性能。
URL
https://arxiv.org/abs/2404.10229
