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.
Primary Subject Area: [Experience] Multimedia Applications
Secondary Subject Area: [Generation] Social Aspects of Generative AI
Relevance To Conference: It is the first exploration using the UIs of LLMs to implement generative text steganography, which generates stego texts and extracts secret messages by using some elaborated prompts.
We construct a keyword set and design an encrypted steganographic mapping to embed secret messages.
Meanwhile, an optimization mechanism based on reject sampling is proposed to ensure the accurate extraction of secret messages and the rich semantics of generated stego texts.
Comprehensive experiments are conducted to evaluate the superiority of the proposed LLM-stega than the state-of-the-art methods in terms of embedding capacity and security, including ADG and Discop.
Supplementary Material: zip
Submission Number: 1017
Loading