Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
Top Cited Papers
- 29 August 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 24 (10), 1547-1551
- https://doi.org/10.1109/lsp.2017.2745572
Abstract
Generative adversarial network has shown to effectively generate artificial samples indiscernible from their real counterparts with a united framework of two subnetworks competing against each other. In this letter, we first propose an automatic steganographic distortion learning framework using a generative adversarial network, which is composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. Via alternately training these two oppositional subnetworks, our proposed framework can automatically learn embedding change probabilities for every pixel in a given spatial cover image. The learnt embedding change probabilities can then be converted to embedding distortions, which can be adopted in the existing framework of minimal-distortion embedding. Under this framework, the distortion function is directly related to the undetectability against the oppositional evolving steganalyzer. Experimental results show that with adversarial learning, our proposed framework can effectively evolve from nearly naive random ±1 embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions. The security performance is also steadily improved with increasing training iterations.Keywords
Funding Information
- NSFC (61772349, U1636202, 61572329)
- NSF of Guangdong Province (2014A030313557)
- Shenzhen R&D Program (JCYJ20160328144421330)
- Faculty Startup Grant of Shenzhen University (2016052)
This publication has 16 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Learning and transferring representations for image steganalysis using convolutional neural networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Ensemble of CNNs for SteganalysisPublished by Association for Computing Machinery (ACM) ,2016
- Context Encoders: Feature Learning by InpaintingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Structural Design of Convolutional Neural Networks for SteganalysisIEEE Signal Processing Letters, 2016
- Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatchElectronic Imaging, 2016
- Going deeper with convolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Stacked convolutional auto-encoders for steganalysis of digital imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Models for Steganalysis of Digital ImagesIEEE Transactions on Information Forensics and Security, 2012