Skip to content

TFILIPS/infohiding-project

Repository files navigation

Information Hiding - Final Project
Real-world Perturbed Quantization

Setup

git clone --recurse-submodules git@github.com:TFILIPS/infohiding-project.git
cd jpeglib
python setup.py install
cd ../conseal
pip3 install .

Prepare Benchmark Data

cd experiments
python .\prepare_data.py \
  --workflow compression juniward naive islow \
  --quality_factors 75 95 \
  --alphas 0.0 0.1 0.2 0.3 0.4 0.5 0.6 \
  --cutoff_range 0 2500 --workers 8

Run Benchmark

cd experiments
python .\benchmark.py \
  --stego_methods juniward naive islow \
  --quality_factors 75 95 \
  --alphas 0.0 0.1 0.2 0.3 0.4 0.5 0.6

Notes:

  • Tests and running ci pipeline are in my fork of conseal.
  • jpeglib implementation was already usable, and I did not change anything, although ifast coefficient extraction is probably incorrect.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages