StegaVision: Enhancing Steganography with Attention Mechanism

TL;DR

This paper introduces StegaVision, a deep learning-based image steganography method that uses attention mechanisms to improve embedding capacity and image quality simultaneously, outperforming previous tradeoff limitations.

Contribution

It proposes a novel encoder-decoder architecture with combined channel and spatial attention modules for enhanced image steganography.

Findings

Attention mechanisms improve embedding capacity and image quality.

Parallel attention configuration yields higher PSNR and SSIM scores.

The method outperforms previous steganography techniques in balancing quality and capacity.

Abstract

Image steganography is the technique of embedding secret information within images. The development of deep learning has led to significant advances in this field. However, existing methods often struggle to balance image quality, embedding capacity, and security. This paper proposes a novel approach to image steganography by enhancing an encoder-decoder architecture with attention mechanisms, specifically focusing on channel and spatial attention modules. We systematically investigate five configurations: (1) channel attention, (2) spatial attention, (3) sequential channel followed by spatial attention, (4) spatial attention followed by channel attention and (5) parallel channel and spatial attention. Our experiments show that adding attention mechanisms improves the ability to embed hidden information while maintaining the visual quality of the images. The increase in the PSNR and SSIM scores shows that using a parallel combination of channel and spatial attention improves image quality and hiding capacity simultaneously. This is in contrast to previous works where there is a tradeoff between them. This study shows that attention mechanisms in image steganography lead to better hiding of secret information. Our code is available at https://github.com/vlgiitr/StegaVision.