Image Disentanglement Autoencoder for Steganography without Embedding
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2293-2302
Abstract
Conventional steganography approaches embed a secret message into a carrier for concealed communication but are prone to attack by recent advanced steganalysis tools. In this paper, we propose Image DisEntanglement Autoencoder for Steganography (IDEAS) as a novel steganography without embedding (SWE) technique. Instead of directly embedding the secret message into a carrier image, our approach hides it by transforming it into a synthesised image, and is thus fundamentally immune to typical steganalysis attacks. By disentangling an image into two representations for structure and texture, we exploit the stability of structure representation to improve secret message extraction while increasing synthesis diversity via randomising texture representations to enhance steganography security. In addition, we design an adaptive mapping mechanism to further enhance the diversity of synthesised images when ensuring different required extraction levels. Experimental results convincingly demonstrate IDEAS to achieve superior performance in terms of enhanced security, reliable secret message extraction and flexible adaptation for different extraction levels, compared to state-of-the-art SWE methods.Keywords
Funding Information
- National Natural Science Foundation of China (61602527,U1734208)
This publication has 29 references indexed in Scilit:
- Image steganography in spatial domain: A surveySignal Processing: Image Communication, 2018
- Robust Coverless Image Steganography Based on DCT and LDA Topic ClassificationIEEE Transactions on Multimedia, 2018
- Automatic Steganographic Distortion Learning Using a Generative Adversarial NetworkIEEE Signal Processing Letters, 2017
- Deep Learning Hierarchical Representations for Image SteganalysisIEEE Transactions on Information Forensics and Security, 2017
- Structural Design of Convolutional Neural Networks for SteganalysisIEEE Signal Processing Letters, 2016
- Coverless Image Steganography Without Embedding2015
- Current status and key issues in image steganography: A surveyComputer Science Review, 2014
- Universal distortion function for steganography in an arbitrary domainEURASIP Journal on Information Security, 2014
- A cautionary note on image downgrading2003
- A digital watermark2002