Generative Steganography with Kerckhoffs' Principle

TL;DR

This paper introduces a novel generative steganography method using GANs that generates secret messages from cover images without modifying them, enhancing security by adhering to Kerckhoffs' principle.

Contribution

The proposed GSK system leverages GANs to generate secret messages from cover images without modification, aligning with Kerckhoffs' principle for improved security.

Findings

GSK can generate messages without altering cover images.

The system's security relies on the secrecy of the extraction key.

Experimental results demonstrate effective message generation using GANs.

Abstract

The distortion in steganography that usually comes from the modification or recoding on the cover image during the embedding process leaves the steganalyzer with possibility of discriminating. Faced with such a risk, we propose generative steganography with Kerckhoffs' principle (GSK) in this letter. In GSK, the secret messages are generated by a cover image using a generator rather than embedded into the cover, thus resulting in no modifications in the cover. To ensure the security, the generators are trained to meet Kerckhoffs' principle based on generative adversarial networks (GAN). Everything about the GSK system, except the extraction key, is public knowledge for the receivers. The secret messages can be outputted by the generator if and only if the extraction key and the cover image are both inputted. In the generator training procedures, there are two GANs, Message- GAN and Cover-GAN, designed to work jointly making the generated results under the control of the extraction key and the cover image. We provide experimental results on the training process and give an example of the working process by adopting a generator trained on MNIST, which demonstrate that GSK can use a cover image without any modification to generate messages, and without the extraction key or the cover image, only meaningless results would be obtained.