Imperceptible Text Steganography based on Group Chat

Text steganography is a technique for hiding secret messages within texts. Previous approaches neglect the contextual relevance of generated stego texts (texts containing secrets) and consistently transmitted secret messages unidirectionally. This behavior is considered anomalous and thus arouses the suspicion of potential attackers. In this paper, we first propose a text steganography framework grounded in the group chat scenario named GCStego, aimed at enhancing the behavior imperceptibility. Additionally, we employ a large language model (LLM) to generate stego texts according to the chatting history and thus boosts the contextual relevance. The proposed scheme is well-suited for secret transmission in group chatting, where multiple agents can pass secret messages through stego texts like regular conversations. Furthermore, we propose token index-based encoding, position filtering and sentence split strategies to deliver the performance. Experimental results demonstrate the superiority of our proposed framework in terms of text semantic controllability, behavioral imperceptibility, and anti-steganalysis ability.