Defining Cost Function of Steganography with Large Language Models
By: Hanzhou Wu, Yige Wang
In this paper, we make the first attempt towards defining cost function of steganography with large language models (LLMs), which is totally different from previous works that rely heavily on expert knowledge or require large-scale datasets for cost learning. To achieve this goal, a two-stage strategy combining LLM-guided program synthesis with evolutionary search is applied in the proposed method. In the first stage, a certain number of cost functions in the form of computer program are synthesized from LLM responses to structured prompts. These cost functions are then evaluated with pretrained steganalysis models so that candidate cost functions suited to steganography can be collected. In the second stage, by retraining a steganalysis model for each candidate cost function, the optimal cost function(s) can be determined according to the detection accuracy. This two-stage strategy is performed by an iterative fashion so that the best cost function can be collected at the last iteration. Experiments show that the proposed method enables LLMs to design new cost functions of steganography that significantly outperform existing works in terms of resisting steganalysis tools, which verifies the superiority of the proposed method. To the best knowledge of the authors, this is the first work applying LLMs to the design of advanced cost function of steganography, which presents a novel perspective for steganography design and may shed light on further research.
Similar Papers
Shifting-Merging: Secure, High-Capacity and Efficient Steganography via Large Language Models
Cryptography and Security
Hides messages in text so no one sees.
The Steganographic Potentials of Language Models
Artificial Intelligence
AI can hide secrets in plain text messages.
Robust Steganography from Large Language Models
Cryptography and Security
Hides secret messages even if text is changed.