End-to-end Trained CNN Encode-Decoder Networks for Image Steganography

TL;DR

This paper introduces a deep learning encoder-decoder network for image steganography that improves payload capacity and image quality, outperforming traditional methods through end-to-end training and a novel loss function.

Contribution

It presents a new CNN-based encoder-decoder architecture, a joint training loss function, and extensive evaluation demonstrating state-of-the-art performance.

Findings

Achieved high payload capacity with good image quality

Outperformed existing steganography methods on multiple datasets

Validated effectiveness across diverse image datasets

Abstract

All the existing image steganography methods use manually crafted features to hide binary payloads into cover images. This leads to small payload capacity and image distortion. Here we propose a convolutional neural network based encoder-decoder architecture for embedding of images as payload. To this end, we make following three major contributions: (i) we propose a deep learning based generic encoder-decoder architecture for image steganography; (ii) we introduce a new loss function that ensures joint end-to-end training of encoder-decoder networks; (iii) we perform extensive empirical evaluation of proposed architecture on a range of challenging publicly available datasets (MNIST, CIFAR10, PASCAL-VOC12, ImageNet, LFW) and report state-of-the-art payload capacity at high PSNR and SSIM values.