Securing Fixed Neural Network Steganography

TL;DR

This paper introduces a key-based fixed neural network steganography scheme that enhances security and visual quality of stego-images, preventing unauthorized secret extraction and outperforming existing methods.

Contribution

It proposes a novel key-controlled perturbation method and an adaptive optimization strategy to improve security and image quality in fixed neural network steganography.

Findings

Prevents unauthorized secret extraction from stego-images.

Achieves higher visual quality than state-of-the-art FNNS.

Effective in real-world applications with ordinary neural networks.

Abstract

Image steganography is the art of concealing secret information in images in a way that is imperceptible to unauthorized parties. Recent advances show that is possible to use a fixed neural network (FNN) for secret embedding and extraction. Such fixed neural network steganography (FNNS) achieves high steganographic performance without training the networks, which could be more useful in real-world applications. However, the existing FNNS schemes are vulnerable in the sense that anyone can extract the secret from the stego-image. To deal with this issue, we propose a key-based FNNS scheme to improve the security of the FNNS, where we generate key-controlled perturbations from the FNN for data embedding. As such, only the receiver who possesses the key is able to correctly extract the secret from the stego-image using the FNN. In order to improve the visual quality and undetectability of the stego-image, we further propose an adaptive perturbation optimization strategy by taking the perturbation cost into account. Experimental results show that our proposed scheme is capable of preventing unauthorized secret extraction from the stego-images. Furthermore, our scheme is able to generate stego-images with higher visual quality than the state-of-the-art FNNS scheme, especially when the FNN is a neural network for ordinary learning tasks.