Neural Cover Selection for Image Steganography

TL;DR

This paper introduces a novel cover image selection method for image steganography using generative models' latent space, improving message recovery and image quality over traditional methods, and providing an information-theoretic analysis of cover images.

Contribution

It proposes a new cover selection framework leveraging pretrained generative models' latent space, enhancing steganographic effectiveness and analyzing message hiding patterns.

Findings

Significant improvements in message recovery.

Enhanced image quality of steganographic covers.

Message hiding occurs mainly in low-variance pixels.

Abstract

In steganography, selecting an optimal cover image, referred to as cover selection, is pivotal for effective message concealment. Traditional methods have typically employed exhaustive searches to identify images that conform to specific perceptual or complexity metrics. However, the relationship between these metrics and the actual message hiding efficacy of an image is unclear, often yielding less-than-ideal steganographic outcomes. Inspired by recent advancements in generative models, we introduce a novel cover selection framework, which involves optimizing within the latent space of pretrained generative models to identify the most suitable cover images, distinguishing itself from traditional exhaustive search methods. Our method shows significant advantages in message recovery and image quality. We also conduct an information-theoretic analysis of the generated cover images, revealing that message hiding predominantly occurs in low-variance pixels, reflecting the waterfilling algorithm's principles in parallel Gaussian channels. Our code can be found at: https://github.com/karlchahine/Neural-Cover-Selection-for-Image-Steganography.