Generating steganographic images via adversarial training

By Jamie Hayes, George Danezis. 2017

337 citations recorded by the source corpus.

Adversarial training has proved 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 the existence of 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. We also show that supervised training of our adversarial model 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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Recent Progress on Generative Adversarial Networks (GANs): A Survey (2019, background): “Furthermore, in information hiding, Hayes and Danezis [82] introduced the adversarial technology into steganography, which provides the novel idea for researchers to address such problems.”
Robust Invisible Video Watermarking with Attention (2019, methodology): “Steganography with DL for still images has recently been investigated [32, 9] and used for hiding a video within another video in [30].”
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data (2020, methodology): “Recent works replace hand-crafted hiding procedures with neural network encoding [4, 18, 45, 58, 55, 42, 33].”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, methodology): “GANs have been widely used in many other areas such as malware detection [434], chess game playing [435], steganography [436]–[439], privacy-preserving [440]–[442], social robot [443], and network pruning [444], [445].”
StegaStamp: Invisible Hyperlinks in Physical Photographs (2019, background): “The most relevant work to our proposal are methods that utilize deep learning to both encode and decode a message hidden inside an image [5, 21, 43, 47, 51, 54, 44].”
HiDDeN: Hiding Data With Deep Networks (2018, methodology): “Figure 7 compares our results with [21]; at double their bit rate we achieve lower error and generate images much closer to the cover image.”
SteganoGAN: High Capacity Image Steganography with GANs (2019, methodology): “…they are also more limited than their traditional counterparts: they often impose special constraints on the size of the cover image (for example, (Hayes & Danezis, 2017) requires the cover images to be 32 x 32); they attempt to embed images inside images and not arbitrary messages or bit…”
HiNet: Deep Image Hiding by Invertible Network (2021, background): “Recently, some deep learning models [2,12,20,34–37, 39– 41] have been proposed for steganography , Image hiding is an important research direction of steganography, which attempts to hide a whole image into another one.”