Releases: zeruniverse/CryptoStego
Releases · zeruniverse/CryptoStego
v3.0
This release is based on neural networks. I trained two versions of models:
robustness model
More robustness against compression, photo editing etc. But less visually similar to original image.
(MSerial#: RAWMS10RE5EP3)
visual similar model
More similar to original image but providing less robustness.
(MSerial#: RAWMS100RE5EP9)
There're no plans to release model training code as organizing those code takes too many efforts.
v1.8
Integrated a better random number generator
Added more contents to README
v1.6
I rewrite most of code and add following features:
- JPEG style quantization
- More flexible on which frequency bands to write data on frequency space
- Use reference blocks to provide robustness to image editing
- Add support to CbCr downsampling
- Re-designed the order determination algorithm, brining down complexity from O(N^2) to O(N)
v1.5
Significantly better performance!
v1.3
This JS library supports all browsers with HTML5.
Download cryptostego.min.js below to start!
v1.0
Download cryptostego.min.js below to start!