Cover-separable Fixed Neural Network Steganography via Deep Generative Models

TL;DR

This paper introduces Cs-FNNS, a novel neural network steganography method using deep generative models and perturbation search to hide multiple secret images with high imperceptibility and robustness against detection.

Contribution

It proposes a cover-separable fixed neural network steganography approach that improves imperceptibility and allows hiding multiple secret images using a new perturbation search algorithm.

Findings

Superior visual quality and undetectability demonstrated in experiments

Effective hiding of multiple secret images for different receivers

Enhanced performance over existing FNNS methods

Abstract

Image steganography is the process of hiding secret data in a cover image by subtle perturbation. Recent studies show that it is feasible to use a fixed neural network for data embedding and extraction. Such Fixed Neural Network Steganography (FNNS) demonstrates favorable performance without the need for training networks, making it more practical for real-world applications. However, the stego-images generated by the existing FNNS methods exhibit high distortion, which is prone to be detected by steganalysis tools. To deal with this issue, we propose a Cover-separable Fixed Neural Network Steganography, namely Cs-FNNS. In Cs-FNNS, we propose a Steganographic Perturbation Search (SPS) algorithm to directly encode the secret data into an imperceptible perturbation, which is combined with an AI-generated cover image for transmission. Through accessing the same deep generative models, the receiver could reproduce the cover image using a pre-agreed key, to separate the perturbation in the stego-image for data decoding. such an encoding/decoding strategy focuses on the secret data and eliminates the disturbance of the cover images, hence achieving a better performance. We apply our Cs-FNNS to the steganographic field that hiding secret images within cover images. Through comprehensive experiments, we demonstrate the superior performance of the proposed method in terms of visual quality and undetectability. Moreover, we show the flexibility of our Cs-FNNS in terms of hiding multiple secret images for different receivers.