Automatic Steganographic Distortion Learning Using a Generative Adversarial Network

By Weixuan Tang, Shunquan Tan, Bin Li, Jiwu Huang. IEEE Signal Processing Letters, 2017

361 citations recorded by the source corpus.

How researchers see this paper

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

StegaStamp: Invisible Hyperlinks in Physical Photographs (2019, methodology): “his paper is to dramatically increase the robustness and performance of steganography so that it can retrieve an arbitrary hyperlink in real-world scenarios. Most previous work on image steganography [4,15,33,34,36] 1 arXiv:1904.05343v1 [cs.CV] 10 Apr 2019 Message 1010. .. 001 Encoder StegaStamp Cor”
DEEP NEURAL (positive): “Generative adversarial networks (GANs) have shown to effectively generate artificial data indiscernible from their real counterparts [8].”
Deep Residual Network for Steganalysis of Digital Images (2019, background): “A lucrative possibility that has already received attention from researchers [55] is to let two competing networks design the embedding algorithm within the generativeadversarial network (GAN) [24] setup that essentially mimics the game played by the steganographer and the steganalyst.”
SteganoGAN: High Capacity Image Steganography with GANs (2019, background): “These existing proposals range from training neural networks to integrate with and improve upon traditional steganography techniques (Tang et al., 2017) to complete end-to-end convolutional neural networks which use adversarial training to generate convincing steganographic images (Hayes & Danezis,…”