StegoAgent: A Generative Steganography Framework Based on GUI Agents

Abstract: Steganography is a technology that discreetly embeds secret information into the redundant space of a carrier, enabling covert communication. As generative models continue to advance, steganography has evolved from traditional modification-based methods to generative steganography, which includes generative linguistic and image based forms. However, while large model agents are rapidly emerging, no steganographic method has utilized their potential despite the stable redundant space in their action processes. Inspired by this insightful observation, we propose a steganographic method leveraging large model agents, employing their actions to conceal secret messages. In this paper, we introduce StegoAgent, a generative steganography framework based on graphical user interface (GUI) agents, which effectively demonstrates the remarkable potential and effectiveness of large model agent-based steganographic methods.

Keywords: generative steganography; GUI agent; action