Skip to content

docs: fix Hiding spelling #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
leno23 wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

docs: fix Hiding spelling #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# DeepSteg
## Implementation of _Hidding Images in Plain Sight: Deep Steganography_ in Pytorch
## Implementation of _Hiding Images in Plain Sight: Deep Steganography_ in Pytorch

This is an unofficial implementation in Pytorch of _Hidding Images in Plain Sight: Deep Steganography_ **by Shumeet Baluja (NIPS 2017)** for the Global NIPS Paper Implementation Challenge. Here is the [original paper](https://papers.nips.cc/paper/6802-hiding-images-in-plain-sight-deep-steganography).
This is an unofficial implementation in Pytorch of _Hiding Images in Plain Sight: Deep Steganography_ **by Shumeet Baluja (NIPS 2017)** for the Global NIPS Paper Implementation Challenge. Here is the [original paper](https://papers.nips.cc/paper/6802-hiding-images-in-plain-sight-deep-steganography).

### History

Expand All @@ -24,18 +24,18 @@ Steganography is the art of hidding a piece of information in a carrier which, a
> all of the available bits.

### Idea
The architecture includes a Prep Network, a Hidding Network and a Reveal Network. Input is secret and cover images and output is hidden image (output of Hidding Network) and output image (output of Reveal Network).
The architecture includes a Prep Network, a Hiding Network and a Reveal Network. Input is secret and cover images and output is hidden image (output of Hiding Network) and output image (output of Reveal Network).

![Idea](https://github.com/lesscomfortable/DeepSteg/blob/master/Images/DeepStegIdea2.png)

Source: Hidding Images in Plain Sight: Deep Steganography, Shumeet Baluja, 2017
Source: Hiding Images in Plain Sight: Deep Steganography, Shumeet Baluja, 2017

### Errors
Error Term 1 (difference between cover and hidding image) is backprops only through first two networks while Error Term 2 (differnce between secret and output image) backprops through all four networks.

![Errors](https://github.com/lesscomfortable/DeepSteg/blob/master/Images/DeepStegIdea.png)

Source: Hidding Images in Plain Sight: Deep Steganography, Shumeet Baluja, 2017
Source: Hiding Images in Plain Sight: Deep Steganography, Shumeet Baluja, 2017

### Results

Expand Down