Linguistic Generative Steganography With Enhanced Cognitive-Imperceptibility

In recent years, linguistic generative steganography has been greatly developed. The previous works are mainly to optimize the perceptual-imperceptibility and statistical-imperceptibility of the generated steganographic text, and the latest developments show that they have been able to generate steganographic texts that look authentic enough. However, we noticed that these works generally cannot control the semantic expression of the generated steganographic text, and we believe this will bring potential security risks. We named this kind of security challenges as cognitive-imperceptibility. We think this is a new challenge that the generative steganography models must strive to overcome in the future. In this letter, we conduct some preliminary attempts to solve this challenge. Experimental results show that the proposed methods can further constrain the semantic expression of the generated steganographic text on the basis of ensuring certain perceptual-imperceptibility and statistical-imperceptibility, so as to enhance its cognitive-imperceptibility.

Automated summary

Linguistic generative steganography has seen significant developments in recent years, with an emphasis on optimizing the imperceptibility of generated steganographic text. However, a new challenge of cognitive-imperceptibility has been identified, highlighting the need to control semantic expression in order to mitigate potential security risks. Preliminary attempts have shown promising results in enhancing the cognitive-imperceptibility of generated steganographic text.