Generative Steganography Network

TL;DR

This paper introduces an advanced generative steganography network that generates realistic stego images directly from secret data, utilizing mutual information, adversarial training, and novel modules to improve security, capacity, and image quality.

Contribution

It proposes a new GSN model with mutual information, secret block, and hierarchical gradient decay, enhancing stego image realism, security, and secret embedding capacity.

Findings

Outperforms existing steganography methods in visual quality and security.

Achieves high secret extraction accuracy with mutual information mechanism.

Demonstrates robustness against steganalysis detection techniques.

Abstract

Steganography usually modifies cover media to embed secret data. A new steganographic approach called generative steganography (GS) has emerged recently, in which stego images (images containing secret data) are generated from secret data directly without cover media. However, existing GS schemes are often criticized for their poor performances. In this paper, we propose an advanced generative steganography network (GSN) that can generate realistic stego images without using cover images. We firstly introduce the mutual information mechanism in GS, which helps to achieve high secret extraction accuracy. Our model contains four sub-networks, i.e., an image generator ($G$), a discriminator ($D$), a steganalyzer ($S$), and a data extractor ($E$). $D$ and $S$ act as two adversarial discriminators to ensure the visual quality and security of generated stego images. $E$ is to extract the hidden secret from generated stego images. The generator $G$ is flexibly constructed to synthesize either cover or stego images with different inputs. It facilitates covert communication by concealing the function of generating stego images in a normal generator. A module named secret block is designed to hide secret data in the feature maps during image generation, with which high hiding capacity and image fidelity are achieved. In addition, a novel hierarchical gradient decay (HGD) skill is developed to resist steganalysis detection. Experiments demonstrate the superiority of our work over existing methods.