Generating Steganographic Images via Adversarial Training
arXiv:1703.00371
Abstract
Adversarial training was recently shown to be competitive against supervised learning methods on computer vision tasks, however, studies have mainly been confined to generative tasks such as image synthesis. In this paper, we apply adversarial training techniques to the discriminative task of learning a steganographic algorithm. Steganography is a collection of techniques for concealing information by embedding it within a non-secret medium, such as cover texts or images. We show that adversarial training can produce robust steganographic techniques: our unsupervised training scheme produces a steganographic algorithm that competes with state-of-the-art steganographic techniques, and produces a robust steganalyzer, which performs the discriminative task of deciding if an image contains secret information. We define a game between three parties, Alice, Bob and Eve, in order to simultaneously train both a steganographic algorithm and a steganalyzer. Alice and Bob attempt to communicate a secret message contained within an image, while Eve eavesdrops on their conversation and attempts to determine if secret information is embedded within the image. We represent Alice, Bob and Eve by neural networks, and validate our scheme on two independent image datasets, showing our novel method of studying steganographic problems is surprisingly competitive against established steganographic techniques.
9 pages
References in corpus (1)
Cited by in corpus (36)
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- SteganoGAN: High Capacity Image Steganography with GANs
- Generative Steganography Network
- Robust Invisible Video Watermarking with Attention
- Multi-Image Steganography Using Deep Neural Networks
- StegaStamp: Invisible Hyperlinks in Physical Photographs
- Invisible Steganography via Generative Adversarial Networks
- Responsible Disclosure of Generative Models Using Scalable Fingerprinting
- Convolutional Video Steganography with Temporal Residual Modeling
- DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers
- Deep Learning for Predictive Analytics in Reversible Steganography
- AAG-Stega: Automatic Audio Generation-based Steganography
- Lost in the Digital Wild: Hiding Information in Digital Activities
- Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach
- Recent Advances of Image Steganography with Generative Adversarial Networks
- Built-in Vulnerabilities to Imperceptible Adversarial Perturbations
- Digital Cardan Grille: A Modern Approach for Information Hiding
- HiDDeN: Hiding Data With Deep Networks
- NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature
- The Reincarnation of Grille Cipher: A Generative Approach
- Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective
- Self-Contained Stylization via Steganography for Reverse and Serial Style Transfer
- On the predictability in reversible steganography
- PixelSteganalysis: Destroying Hidden Information with a Low Degree of Visual Degradation
- Generative Steganography by Sampling
- VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network
- Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks
- Multi-Stage Residual Hiding for Image-into-Audio Steganography
- Source Mixing and Separation Robust Audio Steganography
- Robust watermarking with double detector-discriminator approach
- Embedding Novel Views in a Single JPEG Image
- Learning Symmetric and Asymmetric Steganography via Adversarial Training
- Hiding Information in Big Data based on Deep Learning
- Learning Goals from Failure
- A Review of Computer Vision Methods in Network Security
- Multitask Identity-Aware Image Steganography via Minimax Optimization