StegOT: Trade-offs in Steganography via Optimal Transport
This addresses mode collapse in steganography for secure image hiding, though it appears incremental as it builds on existing autoencoder methods with a new module.
The paper tackles the problem of mode collapse in image steganography by proposing StegOT, an autoencoder-based model that uses optimal transport theory to balance information between cover and secret images, resulting in improved quality of both stego and recovered images.
Image hiding is often referred to as steganography, which aims to hide a secret image in a cover image of the same resolution. Many steganography models are based on genera-tive adversarial networks (GANs) and variational autoencoders (VAEs). However, most existing models suffer from mode collapse. Mode collapse will lead to an information imbalance between the cover and secret images in the stego image and further affect the subsequent extraction. To address these challenges, this paper proposes StegOT, an autoencoder-based steganography model incorporating optimal transport theory. We designed the multiple channel optimal transport (MCOT) module to transform the feature distribution, which exhibits multiple peaks, into a single peak to achieve the trade-off of information. Experiments demonstrate that we not only achieve a trade-off between the cover and secret images but also enhance the quality of both the stego and recovery images. The source code will be released on https://github.com/Rss1124/StegOT.