Search papers, labs, and topics across Lattice.
This paper introduces a novel black-box text steganography method leveraging a dynamic codebook generated via a shared session configuration and a multimodal large language model. The approach uses an encrypted steganographic mapping for embedding secret messages during caption generation, and employs a feedback optimization mechanism with reject sampling to improve extraction accuracy. Experiments demonstrate superior embedding capacity and text quality compared to white-box methods, along with enhanced practicality and flexibility compared to existing black-box paradigms in online social networks.
Achieve secure and flexible text steganography by dynamically generating codebooks with multimodal LLMs, eliminating the need for fixed codebooks or shared extraction prompts.
With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance. However, existing methods still have some issues: (1) For the white-box paradigm, this steganography behavior is prone to exposure due to sharing the off-the-shelf language model between Alice and Bob.(2) For the black-box paradigm, these methods lack flexibility and practicality since Alice and Bob should share the fixed codebook while sharing a specific extracting prompt for each steganographic sentence. In order to improve the security and practicality, we introduce a black-box text steganography with a dynamic codebook and multimodal large language model. Specifically, we first construct a dynamic codebook via some shared session configuration and a multimodal large language model. Then an encrypted steganographic mapping is designed to embed secret messages during the steganographic caption generation. Furthermore, we introduce a feedback optimization mechanism based on reject sampling to ensure accurate extraction of secret messages. Experimental results show that the proposed method outperforms existing white-box text steganography methods in terms of embedding capacity and text quality. Meanwhile, the proposed method has achieved better practicality and flexibility than the existing black-box paradigm in some popular online social networks.
