Implementation of the hybrid deep-learning steganalytic framework described in:
J. Zeng, S. Tan, B. Li, and J. Huang, “Large-scale JPEG steganalysis using hybrid deep-learning framework,” arXiv:1611.03233, 2016. [Online]. Available: http://arxiv.org/abs/1611.03233
Contact: [email protected]
'data_preparation/' - the scripts used to generate the dataset.
'datasets/' - the instruction regarding to the datasets used in the experiments.
'dctrqt_caffe/' - The patches to Caffe with our implemented layers.
'image_lists/' - the lists of the ImageNet images used in the experiments and the shell script used to generate them.
'protos/' - the protos and the trained Caffe models.