Open AccessA new JPEG image steganalysis technique combining rich model features and convolutional neural networks
Author(s) -
Tao Zhang,
Hao Zhang,
Ran Wang,
Wu Yun
Publication year - 2019
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2019201
Subject(s) - steganalysis , convolutional neural network , pattern recognition (psychology) , jpeg , discrete cosine transform , computer science , artificial intelligence , steganography , classifier (uml) , artificial neural network , feature extraction , image (mathematics)
The best traditional steganalysis methods aiming at adaptive steganography are the combination of rich models and ensemble classifier. In this study, a new steganalysis method for JPEG images based on convolutional neural networks is proposed to solve the high dimension problem in steganalysis from another aspect. On the basis of the original rich model, the algorithm adds different sizes of discrete cosine transform (DCT) basis functions to extract different detection features. Different features are combined at the fully connected layer through inputting 2-D feature values to the neural network convolutional layer for predictive classification. Experimental results show that convolutional neural networks as classifiers do not require a large number of training samples, and the final classification performance is better than that of the original ensemble classifier.